diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..8289c10adf6c83b3085db752013d0d7d7562cf49 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,10207 @@ +{ + "metadata": { + "ParamSize": 709, + "ParamBytes": 18431289344.0, + "BitsPerParam": 4.500392846312253 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 389283840, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 152064, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 389283840, + "byteOffset": 0 + } + ], + "md5sum": "d0bab2c33f66d28920bd728fbe2aa27f" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 48660480, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 152064, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 48660480, + "byteOffset": 0 + } + ], + "md5sum": "23c04d001ab8fea5b40ac4b894255304" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 389283840, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 152064, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 389283840, + "byteOffset": 0 + } + ], + "md5sum": "9afe8adacae1bf542102e90ddd704b7f" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 48660480, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 152064, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 48660480, + "byteOffset": 0 + } + ], + "md5sum": "f08665f1908db3fdd521220f4f3cda45" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "ca081aa88683e4dbb93f76141ef0de5e" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "1b429490ad74e4a313f0552ee8ce765b" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.0.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "dc684201c974714b4ceb483267fe2d6e" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 28870656, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 10240 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 8857600 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 26552320 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 26562560 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 26576896 + } + ], + "md5sum": "30b43de0525975c2db0258fd512a3b21" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "883eb02b681fcd2e87c48c9e9f979cf4" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "351f74d8342707308dde419f748b25b9" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "392b00eab66c397fe3f1cee31fd324b1" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.1.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "c8378305459a10b81cfd354ad266c821" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.1.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.1.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "1fa936633feac6f2a3c57cc64ce2c702" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "e52d28b4e44298a173dc17b459c0beca" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "67f9030ef41561a422be430eb26e7ab0" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "4fb3e39489eb9ac6733e4a7c7c876f4e" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.10.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "de24578d96c5897a7c7319778b74fe0c" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.10.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.10.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "cc68761b6e8a1be4fbf5a0238e475e4b" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "25e8d10b6536e54f02f3384ad551aa43" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ba18e8edd5fd209ee2ded9960b35fe46" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "2f08c5b8cb6619e7918c92487608de34" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.11.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "ce392127e1d2ef2a941ebcfbb09eb57e" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.11.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.11.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "d12f4d723f80778974b50d6ace034c65" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "d7d15398f76a24976f05cb7a831dc421" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "b45e96bdaf2ee6c5b98da9c8ab983258" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "ee190bba0fe2063178e88f1d9fbc14e2" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.12.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "9fa4a18261196e0e5670ac2b0bb3982a" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.12.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.12.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "10577a5fd55ce2bd97bfbfca60c6a36a" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "9dfba420aeec2e0834f6c0aa8a59279b" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "cec417de66e50ac63184a42845ccfa9d" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "1ff2843ac817375d2d536358182a6acf" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.13.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "5e819b3ac534f2f9ca14028712a18c00" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.13.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.13.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6ba344f936504ca2a3e2749e55ccc802" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "e10e2d6a61189518724b87a36de67a8e" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "dfa78fd047b9623b84b225dea1f0c072" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "d9f781fef18d8e7b23d529dd36e088c4" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.14.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "c3e7991790e3da06bd102b18b4bca275" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.14.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.14.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "1e8e0fb9e7a8ee79e8c1dbe9e36567d4" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "8aadc6a672a0b8f197c6f5ab38512a4a" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "98ea96653bd2d58fa7e76be35a0ddf3d" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "025dedb289852ed844df875cb80af2d0" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.15.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "46bbb5e3c02e568e659a435a7e69b9ed" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.15.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.15.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "ee12636b9623770c9ffa9f7a498d6be1" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "d693fa41c91c782c41b406a62f56c56b" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "88236ad328979925ea5016a1152e8c49" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "d030f2a64e8c406b2b533793ca26a1a3" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.16.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "3612a0f22d3e41938b83eb95c9a4c4fb" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.16.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.16.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "fa2ba32cd6be3b6fb0c83d1467510f59" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "bbdd681edf1610c39db01bac42e44929" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d13b23c82e6f684f39002205ada6ca26" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "87f2be148884c9bfc28275984edb0f72" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.17.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "360c817f70d3c7545ee830681c234d0b" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.17.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.17.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "5051de162b8566098a2589325e427b7a" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "1e17c5552fe0d28d710be3ae42114f2e" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a9b8c0e798f1446446be44ffa7cd2b46" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "beaa2f2b5f090ee9f5ac089c03ff9679" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.18.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "c3d94e0ae12e882ef5727cc815d20411" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.18.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.18.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "899f7d73daa949cc3fe006add712f345" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "6bc05e6006f97a71b4c74ec40b1bd83c" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "916dbdd5ad207f96ac13c18f19ff72bd" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "6e70941aad6da4c20c0c1f700bf6e8e8" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.19.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "7472f4908cdd3086ffc6787b30a60211" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.19.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.19.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "ddb0b0d689444f89eb2fb81996712f63" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "85fc38a44702a497ce6a18d140f1923a" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "212ed328dc079c859a24af3db761c358" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "61dad564c4b55f7999a0883d7874c9a6" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.2.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "9201f265c97fc7b293c7de4ac368a136" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.2.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.2.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "430249e04913f0cb3a9ed61788f44678" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "1c357339ef01db4f0593b49d7e921777" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "f206bc1aa0a1f304cf7cb8331867f15a" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "493f921d9bd3b5ccc364b00d056bd8b1" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.20.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "c64fcf9a4b86ebd5c230eb6bfcfe12b6" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.20.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.20.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "b933506094bbf2d78d1ef899517e12b0" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "ec680b124905c918c6bf3d1c5f183ebd" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "b1e5285370defa2abe621d5eff97ee20" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "e915a7c40c0d0fd42b6ad2691bc68bf7" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.21.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "ea2477d6fb1f69e43e5676d862070f79" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.21.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.21.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "15c05ae3dbec980db1fea78e811a2d48" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "bc703698503a9df3769aa08f2aa08e7c" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "7c5d7dd4fb58372cacfd3212e9bf83a2" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "d0480e8b83e02b891fd165122aa088ae" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.22.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b3e6206b18c97fd1650e02b6e0ad2b06" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.22.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.22.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "31e7b8cd6252743179215c3d9e8f37ab" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "e89ebe7995a712b0225582c304b7c153" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "1b886210d24556afa49e87b7e7b0f1f1" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "e4036f111c86fbfd8d6d63864fbdd7a5" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.23.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "ae2fef9d20104cad8e87314d029a0586" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.23.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.23.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "5948f6b117c0f471dc2c055f9b9bb152" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "6bcd5bb7e7f199d97bbb5f22b88d1c2f" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "85398f51004d93e9697328dfa27c8cdd" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "8b4994d8deb801de50452ae03caf94fd" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.24.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "848951e3c0ba7336d2935f9310ae56a9" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.24.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.24.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "f3449379ae1eac6c8b7772730821103a" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "4128bc650d1563deee1f12522e93593f" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "561c3a9197bc68d00e889327f08bb7c6" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "3dc9111f4052b7bf075dabb4df67289a" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.25.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b56b481910cb00b21e58fa2e0076e7b2" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.25.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.25.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6544f0361ba55a17c7048b2709c79494" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "39aa67c0f07be02d3b6e9647e9240bd5" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "1c5ac8333ba18b0dd51bf93990c83b05" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "c2873d935c4030d5cf1adccfdfbd9692" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.26.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "3ae378a1a3cab9e282bead6b417036b8" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.26.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.26.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "37fecc3683d68901f3736e3fd6824c67" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "b173dec9534d3ea28dbba9106239871b" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "2a359150b20c6662d10ccba80ef4901e" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "02d29b17dfbac1e5c85b9098a44f407f" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.27.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "995e021820f29f2e04ead649efc9ccdc" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.27.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.27.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "5fd21920e9582bdc0a070ef56e87ec92" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "cd27351dfc5c2ae1a1fc00ae2a3705b2" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "3252411f4d7c28f91c60d595caec461f" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "b28ce562a7b4f6508ad22bdb8713827e" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.28.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "79daa60c45443e9275781c74fe0290f1" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.28.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.28.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "34b35505f0b2aea6b52dfca8ac4da302" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "e5037f5006bb57bb2ee1f51bab1f1ecc" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ee3874eb464e5354128edb471edb2c48" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "7c3d07a36ea877e07e96ec4c44af56ee" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.29.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b234940cb1c4d157b07eae573e232684" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.29.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.29.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "a2f2cdc613668d4a32ad44ea471f7eca" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "56fbf6dc52a12f92785b72e4e28f2b8d" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "fbc268ba22b4f0032adfe5a8d8207c81" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "7a1e53c7ae6d9c0e508c7d4b0f2b88ef" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.3.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "993ead2a336c79fc5c25889ca6623486" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.3.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.3.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6c24339bcb2a6ea949c2139e003f38cb" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "a3cc2caead5a0519b56e1648c2c6ffd3" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "4078429b77ddf0cd77633f894148b40a" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "db460928c5d01badbd39e962db1a0708" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.30.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "c84f12e290a0b7de388181f2260edf06" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.30.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.30.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "c34156b5ec46d2d12ecea2aa473f98d7" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "f57fb3d2394d48a3c3305f46335eb081" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "e82fcd66f9d78f0e6237285dfe341bb6" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "6600f138103612d56d6ff8ee7ea3e700" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.31.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b2b2289ae1f32c57b5712424cbf35df7" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.31.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.31.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6ca67cd9e5bf84867a385538b9641802" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "8bc373b92222790f3d9a9d6004aa55c2" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "e3d8ef0717382aa7d7730789ce326034" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "d24595aae28692502fb12c833d6dc8c7" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.32.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b57c4c58c53fa7f22479e287def0ce2f" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.32.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.32.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "e8583c4a067d0bae356a8ffdab40c3bc" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "8a48268f638db0597a5cb2266dd00b95" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "0e3dbd48a5ee4efc89ec142bb0962988" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "2ffeb1d73ad985f6f1272c23d8882553" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.33.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "5efd14918633bb10f5b449dbdface259" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.33.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.33.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "f642b3de66631bc368fbbf07740d7335" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "0f6b943590654b360a5beb617cfe93e6" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "208d2b19d183bbd5fa70d999e6b00c3f" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "a9ddda4027503c79c53306c44fcf9cc4" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.34.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "66239e6ba0c18e2845524d003ae4c098" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.34.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.34.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "34e406f2c5d359a9c2f5312a06aed5b8" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "cb847b083831320f07d59061f561cfa3" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "7242d87956afe655de94f8353ac45e70" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "75d7923697d59fdeffd3e3346ef9a404" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.35.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "3bd17594a1bf9139f731493a7d35f929" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.35.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.35.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "61306ed78c15a5c5aaad2ea84a93b180" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "ebca0139f2e14d82fcf472120fada4a2" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "5c5b7f7be7c4ea5101e3a95fe269a20a" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "7a894ac429f10674a8240006d8d655b9" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.36.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "66d3f22ce0ba6d4fb38a645e96393173" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.36.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.36.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "2754893016e9b3f88ff9d20dafa8d443" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "e5746a40b125af73c30a033fd465e2b0" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d302665378ccf8aeef836e647bbcff06" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "7fcd096c2b090457dd5788e47ac1f578" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.37.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "6460bead6be6454ab865506d406ef97d" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.37.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.37.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "0524bb13a2a79304d0a4de532c42c15e" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "e64479dba2685aff5c23ddee217cc19a" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a2bc1f0b25e7ebc38ca58bd1c4124a1e" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "3defd64682e087ab790f44425226d73b" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.38.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "47674799c994f9851c6b25f710e53f8c" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.38.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.38.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "724fa2967d19c65fef70e4eceae0114e" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "097768d66fc4289b47ce5bfa69b9310f" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "e74c0958f1da18e0e50c18e365d18734" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "2e9c54ff31ef4b1bbab6aceef38b54c3" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.39.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "e90412f59fc1ddd68012f0cb5462efd4" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.39.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.39.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "91cdfea275530898e955fc69d5fb8815" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "85097c0634f7ee663aaaf8bb846596a7" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "3b87fccaa180cbfa7d8aac56735a348a" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "c5de8b4dc79b6bb379c156c7b618233e" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.4.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "6bff386e0db5d616b6ef585037ad79c6" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.4.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.4.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "637985fad61c4f3d11429ad63127be08" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "1d121337b6af4208fdfcd0dc2dd9ecfa" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "354f89179e538172636e0b28f923dcd3" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "6cc77c081b64617bd15f90c82b3fb58d" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.40.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "42fffff60b313b32558309437f9476fe" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.40.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.40.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "da72f8b845e03ff070b69a05fa1bfc81" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "544c51d4b655cbd9401ed20260488d91" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d6f9dfc8d82a6a323e225d371a9d3cbc" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "3cf523325ca84f5d2a89578fa090f9a8" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.41.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "2e0c54612900dc557416e14ca181bab6" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.41.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.41.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "40eb2acce30c7e8829c89aaba8d304f7" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "bdfbea50dacb5a176f139807f01601cf" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "73029da43080808e74226a112362db9c" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "1dfeed5c3b2229a4549940b14762cf3b" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.42.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b5f01c280e4ac89f17eccc47369c91ad" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.42.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.42.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.42.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6ac2c685037a467c29af67858b5e333e" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "57b3d5111601f83f616d6f1d0c304fd6" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a73214f4453db09726df8cb3ada826cb" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "d981460dc063edbad75e0b49edb04a88" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.43.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "583fc91e82036071bc03ea2e1f9f38df" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.42.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.43.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.43.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.43.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "8ad67542e20822fbb59fd01594e6a5b0" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "4e9bd11ec485e40e531fb889b14d3ba4" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a57ba2aa34363ba322e132a8691a30ed" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "efabb32e1c231b375b397d53e626b7f8" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.44.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "efe3cecd6bb2a902334d7219b0387d84" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.43.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.44.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.44.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.44.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "4f8bd3787ad18067760f1593c9836ab4" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "cbf1646438510ac693f732baeda364d6" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "7b284c41718a5efc6a1fcddab8358213" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "bc9119951a950499472af95bd3dfa8e3" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.45.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "0c49c41560368bd392198c384b13b439" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.44.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.45.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.45.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.45.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "176e3897f768fb4d6aaa15c568903296" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "d0ae7fb8592103e9a45b23bd5179b9dc" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "abd6a6c337719f929e576057036b448c" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "5113285f896da8a1d36e6fbaeb5eedc1" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.46.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "30b528881a5a54604a2b8d7051058f34" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.45.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.46.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.46.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.46.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "e6ebd59c5c3ec02a673698aefaa6d56a" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "8a8e05ee48e6645b1e9bd11cd2d4f0ee" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "5858affd29a29de4144aa004745d79a5" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "7b63198a9729f2309a5125d45ec0cd71" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.47.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "01d99c1120bdc23af06359971865d17f" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.46.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.47.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.47.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.47.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "e768cb7291ed1f75f6c0ff493b2d2477" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "d4140ff41f6ac26f21da4818204e5990" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "368cddef3bf6470a31c7507d773805dc" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "8be99c7f130b178f6d98560a338d6332" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.48.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "4e8e071fb92d22213d11104b022644e8" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.47.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.48.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.48.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.48.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.48.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.48.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "0a3eeaebe035d0bd47952cdb9937ea11" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "c676c2c05da22efd031546725cb3f9f8" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "905086323f6dfa13afa24cceaf89565b" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "c8bdea89a2b170d6255c3d668d53ccd5" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.49.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "38e6c817abdf91979af98d96bc1ac220" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.48.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.48.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.49.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.49.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.49.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.49.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.49.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "246e002e04f4f8695bc349bbc9c970f5" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "b7f5002758c9eca0bead1d99719048b6" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "fca15f6fd1f505e14883b022e2f04d56" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "dfab114ecacfb2ada66b0c7ef6c38751" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.5.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "3bf1e2d58823105c01c5f6becfc56177" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.49.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.49.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.5.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.5.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "9ee5d793f34551a3e7cb96ed4ca30dfc" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "618f0ccb448694055fc495a374be367b" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ff1efca44725c9e3a3a3d1103d825fd2" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "36b75f701fbf9b0856de38fdb1d07521" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.50.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "55111d639e2c8518fe55ab432a9dfc0f" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.50.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.50.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.50.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.50.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.50.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "7e4f8d3389340f8b01e55eefc556b9fc" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "10daaf04d9e46b8fb8cc2ccd57c4cdb4" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "2236779c2668efbe5b3637797bf74c52" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "1acd50a00ee669e5fe16fee4ee67c059" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.51.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "b31c6a03ecbee80abdc51334fd60f7f0" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.50.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.51.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.51.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.51.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.51.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.51.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "a35b5270ec1ae287b9d4ce39efc433fd" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "4beebff6390bef52f8cb0364e7992192" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "8c756569af0bd7206387dc3f64251179" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "308251dca16bf368ee51b0bae33c326a" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.52.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "8503edc25b473e73675cff0b1f56a760" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.51.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.51.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.52.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.52.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.52.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.52.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.52.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6e5b4cbb1b7b1fa9218c770c889dfd5b" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "2e7a2e4a01968e07e7dc3cc4144a1711" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "3948da35356416ae50776726532d5af4" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "ea6debb9245b5b15a66e5a5ee205947e" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.53.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "a1f28f3ee62e245ec28a988fd6a5eae2" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.52.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.52.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.53.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.53.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.53.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.53.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.53.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "df47ed0b87e7341ac790d9acf2067fe7" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "5bc6cc71c50061f8b652b996e573f7d7" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "8ef94408d218196e49b863a4eef21829" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "e106f70d3eb1b73c5c4fe2c6e7a4ed4b" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.54.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "1b401047d93765aad1173ee10f981da7" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.53.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.53.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.54.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.54.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.54.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.54.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.54.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "e656db96fee15296e8334f3d10fce499" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "8798f8694afac953c58e7feb81b5072a" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "eb5d64f73a3161baa65009f5dc534768" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "46d045b454a908b5ec55f21eaa19be69" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.55.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "4117851dde5c0768fcc066abe6104dfa" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.54.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.55.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.55.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.55.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.55.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.55.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "d2dbcbb56818bba9ece0c3b20ade2cf2" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "bdd19113c15db6bcfb1f9cd29d788038" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "3caa0235b0561bd3d57c348689d2c4fa" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "b33e3fb2c25a7d3103bc853ac9074093" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.56.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "9ec2cbf8a78f1fc58fc45eda65d64421" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.55.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.55.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.56.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.56.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.56.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.56.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.56.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "299f1a76db4c26182dcbb972bc08a55e" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "a5ee09291ff5097248354072c08e95b2" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a1fd6d2f9718c5b0e3fc943f060dcb31" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "09a6315a606e710457e20f1ede132536" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.57.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "913875e7221bd88c0afc338091052725" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.56.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.56.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.57.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.57.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.57.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.57.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.57.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "081db6c143421b4ea6348d519a27ed7d" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "08be1cf78360cc04c8cc35f98886d39a" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "5e4016c92f45fe379420605f3f0a829f" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "de2ff1d77d4a471ac3558c2859add03a" + }, + { + "dataPath": "params_shard_276.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.58.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "44ef565c81f90f9a38c9ac0a51bb8188" + }, + { + "dataPath": "params_shard_277.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.57.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.58.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.58.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.58.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.58.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.58.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "bb650461e56bb38b911783990501bf08" + }, + { + "dataPath": "params_shard_278.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "eb2f0318e8687f9801ea6d0405448b40" + }, + { + "dataPath": "params_shard_279.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a6a84bd4c3166bb45e58fafda373b95f" + }, + { + "dataPath": "params_shard_280.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "882d41de8dfb25aa4e8be8c03326c924" + }, + { + "dataPath": "params_shard_281.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.59.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "aad707c614c599ec26d5d46d05fb1406" + }, + { + "dataPath": "params_shard_282.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.58.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.58.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.59.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.59.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.59.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.59.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.59.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "e190ab1fe2bbbec3a8fe389bc7404b92" + }, + { + "dataPath": "params_shard_283.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "411f11b735f7d97c6c59e7bab1d3768b" + }, + { + "dataPath": "params_shard_284.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "960c5d1f6e4bd2523beee0833b7f1565" + }, + { + "dataPath": "params_shard_285.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "52d3718058cc60bd1aef75bec041c21c" + }, + { + "dataPath": "params_shard_286.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.6.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "37cf7e55110ccce1b26ae8913682b227" + }, + { + "dataPath": "params_shard_287.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.59.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.59.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.6.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.6.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "bfb35d047eb3e2b8e04e06f9a31db1f1" + }, + { + "dataPath": "params_shard_288.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.60.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "cd31ea05f92b1e7adccf2b032ee937ee" + }, + { + "dataPath": "params_shard_289.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "555bf5e761066dbeb91dc1603b854cdf" + }, + { + "dataPath": "params_shard_290.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "c2ef2314a96f5f6e468dcb8c7cf4e04c" + }, + { + "dataPath": "params_shard_291.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.60.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "7a3f6b83169fa7aa2ad790d8fc081e23" + }, + { + "dataPath": "params_shard_292.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.60.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.60.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.60.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.60.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.60.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "b8c5e6a5b419029f08cd942a8cfbde59" + }, + { + "dataPath": "params_shard_293.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "0b24c9261645c07719b7fc68610b2918" + }, + { + "dataPath": "params_shard_294.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "90e3c12020498db256f548b5a27b5e7b" + }, + { + "dataPath": "params_shard_295.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "f4c49c5604b2c1333c6002dc3e2ef296" + }, + { + "dataPath": "params_shard_296.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.61.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "5c4b15eb34f14c31c35cc48401a88c46" + }, + { + "dataPath": "params_shard_297.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.60.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.61.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.61.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.61.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.61.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.61.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "a9eb8d395633f1763e9f5b4a2177780d" + }, + { + "dataPath": "params_shard_298.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "3d93b4f83a0f7b4d0905de07449e31a1" + }, + { + "dataPath": "params_shard_299.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "87342d800a2e6cce0315f90cdd795a10" + }, + { + "dataPath": "params_shard_300.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "8d42a5a840c9b9b7cdde8ba2c4f8a730" + }, + { + "dataPath": "params_shard_301.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.62.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "0f54db194f32f0751d235154824c3600" + }, + { + "dataPath": "params_shard_302.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.61.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.62.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.62.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.62.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.62.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.62.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "f61940485e04009c86462dcae008bd78" + }, + { + "dataPath": "params_shard_303.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "c47e7d87ab2445508ad94397e3cca0bf" + }, + { + "dataPath": "params_shard_304.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a368b13c1b0a8a5d555d305492d4fc8e" + }, + { + "dataPath": "params_shard_305.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "e7f4be23b6a207375e5e7e5dc9362368" + }, + { + "dataPath": "params_shard_306.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.63.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "ef1d4b3e5b99336965222c247dca89ae" + }, + { + "dataPath": "params_shard_307.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.62.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.62.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.63.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.63.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.63.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.63.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.63.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "21748eaf923bd899e558445c2810e6c6" + }, + { + "dataPath": "params_shard_308.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "fad8d025db5286b7a70ae9adc2b90ab8" + }, + { + "dataPath": "params_shard_309.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "08c8651509c4ea8e90c8193180130d79" + }, + { + "dataPath": "params_shard_310.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "7844f57b712d34e9cc35d358ca567d46" + }, + { + "dataPath": "params_shard_311.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.7.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "6a8c16cb25c0ac3b4934a62047715762" + }, + { + "dataPath": "params_shard_312.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.63.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.63.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.7.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.7.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "e0f768516fbeea1dd5e262d3b9f04046" + }, + { + "dataPath": "params_shard_313.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "ca7b691e4ccc966060ebf1f2925670b9" + }, + { + "dataPath": "params_shard_314.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d851d6d4865e793e75af034bcb1daf5a" + }, + { + "dataPath": "params_shard_315.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "283e457fa434c9a4f80006ec4c3be4e6" + }, + { + "dataPath": "params_shard_316.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.8.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "929e914b71ec871227901ad49042e451" + }, + { + "dataPath": "params_shard_317.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.8.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.8.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "6d2c2f3236f079d685eb7654be9aa431" + }, + { + "dataPath": "params_shard_318.bin", + "format": "raw-shard", + "nbytes": 70778880, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 5120, + 3456 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 70778880, + "byteOffset": 0 + } + ], + "md5sum": "9ce66e6cc1a372f3847c5a9e33c1f837" + }, + { + "dataPath": "params_shard_319.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 55296, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "128a45cfceaed994fc507581dbe85f06" + }, + { + "dataPath": "params_shard_320.bin", + "format": "raw-shard", + "nbytes": 17694720, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 55296, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 17694720, + "byteOffset": 0 + } + ], + "md5sum": "ac32a5cb14e620503210314fe41b0506" + }, + { + "dataPath": "params_shard_321.bin", + "format": "raw-shard", + "nbytes": 18350080, + "records": [ + { + "name": "model.layers.9.self_attn.c_attn.q_weight", + "shape": [ + 7168, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 18350080, + "byteOffset": 0 + } + ], + "md5sum": "35bacb47173d435345ee03eb39ffe5a4" + }, + { + "dataPath": "params_shard_322.bin", + "format": "raw-shard", + "nbytes": 25921536, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 5120, + 864 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8847360, + "byteOffset": 14755840 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 23603200 + }, + { + "name": "model.layers.9.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 23613440 + }, + { + "name": "model.layers.9.self_attn.c_attn.q_scale", + "shape": [ + 7168, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2293760, + "byteOffset": 23627776 + } + ], + "md5sum": "fa3299ec967ebed4e5d4fc23b5d7a6ef" + }, + { + "dataPath": "params_shard_323.bin", + "format": "raw-shard", + "nbytes": 14755840, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 5120, + 640 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 5120, + 160 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "model.norm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 14745600 + } + ], + "md5sum": "8c2f72f95167d4e47e6be5141adc7178" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..effecefc456465f391df6f4e2d1800841cba0189 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d485ee57f6c0b040a5cd50617538abbd58fbf38b267fc83a478853492c60c9b6 +size 389283840 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8464059dc49b3410a551e9e08823dedeb6791fc --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53bf47b56d5de3391fa8e00ad962e9c0f7f3c13af6bd2b1d186023ca22af7724 +size 48660480 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..00791f3606f91d2b960eb176f3f3ffb488c25d6d --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3069e1c1040963167f0085016c4fb350321b07d003b5ca2d4e9a9d21ee16083 +size 17694720 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..34289fe465190e3f3dd9f3d215bfc5ce8bc4c6ba --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e84f1f7629a0142c2104da5f3b6b52307c0fffa4e4801d9b399b8de08be67f +size 17694720 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..71bad41a5d160c38d79122b767b19945aab4f8bc --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ad146136b0b6d12b430f96d5cd2860275caf9ecd028743cd71b96b792494bb +size 18350080 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..949e6f6d5e84e67d04f995bced92d25b0f3113e0 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fdf4da724f6f452b245f591f1e48501b17ab26cbbd7b67f95d6eed02b397ee3 +size 25921536 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5cb43a58fec5391adec4f5de63f90a467f3047e --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26dec30cba7e8f6c560ecf64c195711f861096ef432d795e116ea2e74f5628e1 +size 70778880 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..84edc4ba222eecc36d205a60e56dcb2f02f6dd25 --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6866626f643811fe3ab440bd7a50663fcc7979c96b2d7a981f8b301c17676f +size 141557760 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..147e0d6dda98097a6ca4dede7a5d1c16b9083f67 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32cc1a7640b57358766280dbba66514a3988159d29fb41df55ef2ca487d99a01 +size 17694720 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..05f42fb44af6b42c50701fe2a87f6ea330396a1f --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571de4ff521cdf252ddb80f803856857dcde8e3fe5bbb482a84917fe20b320ad +size 18350080 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..ded1752be0ff51198c2d9b49bac3a17077d3e500 --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f590fdd927322b08e25d38dfb899651bed8e1662d5869636a1c6e0d7c82372 +size 25921536 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ed3bef9061d39194b5bbd2c70c388bc973957e6 --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a701e765eda338aa7df4e0ec946ec37ae0e9dd3b258aa1e7a1960a52bc764042 +size 70778880 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..80a2660650a19da2a6c7d007c640f093e481307e --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2b07d5462b9ec2a799768505a7904184e8f07699062c5c628c859b101490c7 +size 141557760 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b00358d9e17353a55ed1b8415da556824f4c40e --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a970c4b5ab069a30efc3b8eb71e595114e0f1439b6472039b7b667a8ec00c0b +size 18350080 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..774202eeec067e17a335af17af2801c4ded9409f --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc61273066705d767fa798c55f0e1d3bf11ae94883655ccef639669a24553c83 +size 17694720 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b61719d7958c9b31249ca94fd8b030cbda402ec --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce21f77b35796e5477d6ee9d831b94924f600f3251b83202c0f2d64df4d9cfc +size 18350080 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5feba274f304432126d247f98c8b5396aee9adf --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4c6fb29169fbb8abb69e4965dfbc9bbfd63605aa96a8e9cb16c444dbd1a09e +size 25921536 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b104d1d77d77f438dae0e1a76e3b5b79d93b134 --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2754c08ee119a158c119b6c0e220a4970f0b3d359c338e0312cf29ae44c62f95 +size 70778880 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..00d470f379189a26042c50869a994f3d5ab196e5 --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c7cf0a18c4f350b3f9c563c3e16e7ba1e1be2c8d6c05255d89edf0e07edcb2 +size 141557760 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..756a832c649751afc5f3e811c92a3b31f7fb0e07 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8910f7f5e9b0a605d109a0a27c4b85ead27c930e9ff2bc6098e1a21b91273740 +size 17694720 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe48809c4d5a93dbe684ec5177db6dd2efe8b7ae --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5eb99ac5d1ed092c0d476d2679514e62c3d367e5371d7489762eaf56945ef62 +size 18350080 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d83e7fde46dc0dd525bf8b791a68aa3c25c749f --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2530c3375bc555ddb0d37388c290ccd9e80f89123544e81e454191cdd987bd10 +size 25921536 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed71da0daa7344778af28dc06ea10dae4ae8f9a6 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:620b20a96712e45bcc6481f54ab7bdb38c1b0cc3f902d4a9b54ee0b6e5e731c4 +size 70778880 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9d7beff503b5666a090497d8733c18f3ca27a6f --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0175a31058e25eb8e8da70810ce616d813c28d193c663d75a376fc357b8b6192 +size 141557760 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..052f5f04a0aca7140044bfcfa45657c5a2dc47ed --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a352a5a40002ce61ff09c72d0b2e33f5bde23fb1495d9a871678d148cd9cf6 +size 25921536 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..6651253e360650379b2a0cfb9c03811e12495006 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9d51c6b3c2438dbfe3b75f42573398276667aa4fe63c965a37266c85a74b0b +size 17694720 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..06fc2aaa7d29814a31c88ec4ff513f43edcdeaea --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ab4af9646c4bde0f225b41d2697c811da2da1a548e450489cd023a67194070 +size 18350080 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1b106c5aa3231b7d347409899113ab374efd01b --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412f653a40f0a2dd4f2ed59e876f555301a8aae996510d2a390ace6612b919ed +size 25921536 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..8866eed61ee19e7100ba6b99c2daa7815e59da52 --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70c25e8bcad76c393356edd0b60f4f097cb88470f442c0823503fd7df335d65 +size 70778880 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ad08f2fe607a5e903f61654416cbce1d68b84c0 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:143e3e2cea6af8eb20f3ed807aae510ef3e9021c28bba4803d48852809c1431e +size 141557760 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..f57d014996c58c203c6a0895de696e6d89005e18 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abfd62c7d33cc55b078c3df15afb5dd9594df9a9fa42d81534a402afa065c206 +size 17694720 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6363f52c9486297a89f009de6990f6cbcc9959e --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e92a3c4ece38f5e45afdc8880fa2087b6785e0c8b00bca9609eb319c2c0c4c +size 18350080 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..a4577a6dce36893c6d56f913062ff14eb567e49f --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5732ecd55f0d8d040235678a2d00e94b8f7b50ff23cd1096accc7f9a62a66bf +size 25921536 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..72363a057ea55d5b5e46a2d1cabd0b464e82df9f --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4750ae899bd33955cdbbeff587811c21b167ba46e59d83908938e52603b822b +size 70778880 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a7de7f523aef2c31075a2587e4744d3201998c7 --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671faf22c939ae63ad52757a941a679574c4ed8f6834d4e62a04961a3e693aad +size 141557760 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..fb1a995abf477d3f6107e98eb67255b028ecf0ef --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5738f450dd5f71a70e32b65530e0a4296f01bdb50a563cd3d63e29b34af44c2e +size 70778880 diff --git a/params_shard_130.bin b/params_shard_130.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d54762e4b63d93542b5a27fcd392b75ae6c2143 --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321f0d6938e554525b210874bcb0d20de54b99156a1497c41fefaccea5525866 +size 17694720 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..d900cbd4ee5a46d8ad7db503a340c3f89b601e89 --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de2ed719fe8befcf07ca2bc57b945c34856f00b05f492915520cde75d73096e +size 18350080 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..67f0e87565454c0130f275322cda19df25240c7b --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c627a06fb220c413c67808b48b9e46a55ffadbc15639598fa4b8e5a7286225 +size 25921536 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b15db84406ce09e1543db3bcbb0ab77e7948e8a --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3937fd08913661960af2aff4b7e134da9731460a81221ba2fa1ba4677fa4b1af +size 70778880 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef50d44c1b57bd35359f1036159d103ed61b739c --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3a0b888db0025ff80b19b7e38598f189f3822291900b6660d5eb4ea3f14bc5 +size 141557760 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea4afa80e244ae48a2d8a1ef9b0af561a83d3bea --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff57e9d663ac400a6843d18348925777267dd9410993a043e4a15d6a2e865cbf +size 17694720 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9abfef0c7620d299b972f23dff3f292d4c99f47 --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62abc94a8826dee6169db76d063c3dd3038c254fa0d76b251eb7abcf4c7b2238 +size 18350080 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa3ecb297be49ded1f7620d28158fc544457796e --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd2c4900969b38ded9ab2f45e27cd4884adce6d93251dd6897df5a9b71c5d1a +size 25921536 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..be97afbc0919e5de1001dd9dbeef55107528b9d5 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55bfe329aadfff64ed5af73d9b6cf0d3a92819e935197c3d77cb82a40a49ae9 +size 70778880 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..edaadc016e48875993ad3a7c0482b5317d017d7a --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df1a30732e2ead529261833b82a7d17200f3f0a515fe559873c8fa0e4bb65e1b +size 141557760 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..d2079a2040a4e8bb4111f759cbdaf6eadeeb6840 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ec33ae4c7fb77c0baa6551ee71cda5fbbef639216528fe9d09eeffe2d8a05f +size 141557760 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..9463d13470c753f9332c71e99b096deeb9ae385f --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7711a9db0e117aa2827a7765e2aaf3e379d79e70e94519b832ec3d9617498637 +size 17694720 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..55628c6c669eb595f8f0efe0d805b4329c260e20 --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ec74fbfdffe56aeb860e6622ba7b4fa75cc4ab349bceaa1b70ad9824abaa40 +size 18350080 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..d42aaefa27985f5382d4a58e9b707e79e1676f75 --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11753171bb412b4332d684d10d8fbbf4563bd0d7cea06cd673ec668f3ca2dcc +size 25921536 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..424e5313c8a6c24228ad8694499960ccb674d782 --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c058b797719c713f50e17fafa6185f3f3cd8d4cc58bf05c0167574c6d2d4d2 +size 70778880 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc8aa0b6793d7a3d6812c42d151f39efce094180 --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2096a0d5450bc48d1f12963925f8675f45db02fddace71f098bc46a5f5f825 +size 141557760 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..7158dccbbd2c0a5320e06e4b9ea2e91d9a8bc143 --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b101bfff1073f8c1bb912c268e2647045b0662198e4709d979bbfaae987eb0b3 +size 17694720 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..12523eed15c41f0a2daa282bd61ad91675a64f54 --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a939ec2b47aed8fb5f1362f02839bd89db217ca7ddde2c0cf7ca08ca8b969d38 +size 18350080 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..c5b4224babcffd52b5f100e23ae8cd3e1c34500d --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774c2624be103b99b450ba3c6b1dde7dc80de5423202267ad8e1767828010ce6 +size 25921536 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5a85c021bf1910990d23b9b66579eac0b7a0fc3 --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1f5f034c0abdf9847a41045ed79e0eaed8fa50ecceb46e1ecce3f2c9747241 +size 70778880 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..b82472a4fe6d7cb0af22af747f63865f2f26358c --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e85967f8efcb58f5276d8953b08828ca3521dd249b678556beeed4daa900860 +size 141557760 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..0962099133c9b5aca1438e679a15f9668fbd8d23 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de905dec3b5c2071ac6a8bc9c65293667580c4ab94fc442ea89c67a3e1a0f670 +size 17694720 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c40bc8517ff7aba87d9abb5a052c3a12ffd2f86 --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84b69cfc3dffbab7def61e027ef821675f3dd9df1d0f7d4ba50de66726dcbe6 +size 17694720 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..c874dd31c0a30efbb2b6dad2bd3024525923edcd --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f098fd41093f3259057bc0f59c3bc4d227cb6fcbb0a76a24159162b141c6c6d2 +size 18350080 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..d85952b57e6a923a17389c80ad044e513d2b4911 --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5eca3a16c964d0bd20d2f47ad5fb9b73795292347fe2b8a6f04f3a57a2b60c +size 25921536 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..087f02188ab6de8474dde2ac8932b5222fc4bb0e --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7aedac08b1ddccac533fa603efd422edeccd71db90e62931fd7a6f52b77c79d +size 70778880 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..32ba1970dd0c62b6e7e53bc54c8144ec97a36bf4 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed910ed62a0b68aad5889497efa4d148b7f22681e9665f3527f8ab11a19219b0 +size 141557760 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d5ecd3c021e2b431d542c8ced2849666329453f --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f6e4cbde645acf1b343c9cff073cf5803937f1a75bb25bf5751f822ab2ae4f +size 17694720 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..374d260fbf12aeff510f1b80cac6714d6bf3885e --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d903a75cd6245906cf5793bce6459431983ac8f077e367e233a9a96052415623 +size 18350080 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc4b627ff63d5d6cd4cd5a8d392796d434a300cd --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5938eb66ed407f4937700f75973107ec8353f9d69f101ed5a4bbde196d9f0bc +size 25921536 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..fad3e7db79153c045c25a38aea46a02d9c38691f --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2908a4b2fa370b09516dd3f14ab958b43292243ccd75daa7bc20be3c99f0b294 +size 70778880 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe8d4bc5cb23054be9425196b4c8d44aed70bfa4 --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5259a5268250218da15ab4bcdb1b52267c0b420a2ca163009e19265558e841f +size 141557760 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b608ce24cd6935832c63a42ebf306f61bd8fd24 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72aa3aac26cbea86795d24f0f91cc57262da1e8c68a592b5559306edf7d1bebf +size 18350080 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..94d00e2cac3147c128a2dd7f57daff5fdbe29bab --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2932119a86d1b8e2f8da7bd8d9e1d3b00219bf7707b6235bb7e6bb67232298 +size 17694720 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b9a59c057cdb3422d089c8e9d2a545034f32e8e --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34dc37b21e225fea3f458acc957f035ad68700b082933b296c863646038b8a8 +size 18350080 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c98b537752ee6aabc7c96d111925956dbd1259e --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8671e94a8a4903aec8f91f99e2bc35a0d26de4c37d5d332c6dc0d65c523a7365 +size 25921536 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..94b996f283577552ba6384a60896fcd2070585da --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14eeadcfed689cfc1284d81d5cf25bd4168cb985bcf683f19e5447d6ee28a56 +size 70778880 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..1398af1b74976ef6fc32ab1eb3e984de6b657a7f --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0476abf25d46e9e8033182ce7148e7d95bb18c021af3193f92f51b967277e859 +size 141557760 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..3f3e988862a6ceb433c28885f65283070b7ea72e --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd546000ccc2d9cdd820d456cd3bc6209c76d547e5505e8728c1afb0d384d49 +size 17694720 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..524f77df18db3d17f9f94586a91e68f6cd6e6870 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c2fc92dcc9af7544b28847cd6b04db9894f86c3e522253a5de0d6454f8d758 +size 18350080 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..13c7715cdcc0e59d5c391bca04fa69d900099294 --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccef9e4bc65e060275dc948a1595f7db3487fee788e9b8c34c5c9c12464e2a2d +size 25921536 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..d39f96085c18443b3ae95049644a5fc0f1ede404 --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3142cc21655b95f3df577f15f5c2580d4af9592d317794fe5bef3f12d16f27c +size 70778880 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..ca38a1169c90079377fac7610a5fa7731c511ac2 --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fec6fc271df4990e2172c84ebacb2365b40f8b41cd0c9bedc7b8a36a79868c +size 141557760 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ff9820a78bc5256d5bf427a8bd364684a25ac55 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d33eab9e6c13af7c94a1e365724f72349385b7a68ab37e0383a35d855d9e58e +size 25921536 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..d29597ca5e9dcd3ccfe76e76ab303b5b97cccf16 --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81da35ad15de69f23e3316ae74456f25506f3b7cd9d0eaaf0584f4ac5c3d4d8f +size 17694720 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..256475d671ad760efd908ef130e2fc9dbe20266e --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d36b27a646a34396886b09c47c08c51d1fd45d9ffb808bdf506b5a78b94e97f +size 18350080 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..3f911a3f35549b326d579fd12180039371c92305 --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5232c92da94378ea7229b263c5442cf9e9470ac248f962a512815f4405f8716c +size 25921536 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..4abacfa238c8fcc38edfd6c6acec64087f0b4984 --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0c497af2d373cb749b31c03b2f1dd982cf4b5f43c18c62e50e3c3feeb01438 +size 70778880 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e0b9c118a695ce48b70c310e62ac3b0ec61e25c --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995497081c818449b72d78a197e05660277155a75e39eae8a8c93630d4b23b41 +size 141557760 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..819355cfa2fbc30345e631a64dc9b5d8dcf87c87 --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35370e39f2b3258006f2b2de0b1e03f18682d0a7af4d7aad0b83b70b7c638276 +size 17694720 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..a55ef4e36004692e39c767b67d677f5b8c8a933e --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cae04488f090c3b838b38e8d3e0f9320250b44e807d87959bba3d36b95380c +size 18350080 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..99bd8dc45b158107b957f97c06956d914a76c4cf --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d40f7fd13a86bb46834edc37e7cbd6184b88485d8030132557b54356c91cfe +size 25921536 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..2295e9528779966cd69e831ef45d34558b2b6f6f --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4149f74d1402f9d0e4d7bd202886fd5a88d241f40c6636eaa6b952e688652bd9 +size 70778880 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..6afdf7354186b107aae8825857ebd686a30d5db1 --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35fc4ca9bbcdc036a81f3f821f4bf8205bc11dce5a7ff1625086cf6ccad034a3 +size 141557760 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..cbe8227e0fb047d460af2874ee5107f7561575de --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c662600a28f397b67ebfea0561a07ec58e069bf9adec915f91cf324aed6b1e35 +size 70778880 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..afd3c3540b83a3821502425a863875220d82f3b2 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e1709430cd1469fdfc490754f5dc1f6dd1f88725900cb52815e7742c883630 +size 17694720 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc40f83e74b463002f0ba8bd30a9ac7d42a62768 --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd6c7c3599620bf5d21cba6388386701540cf05518863426ddeaae12bc25e69 +size 18350080 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..48121598a5904feecfc5a203b5738f13a803a6fc --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c136fea33381c417658a898d8e226c65dcc2409868ab329c708895c1f17033ec +size 25921536 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..421558ece9269c7122bf3ce6d235787afd72b2cc --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39dbe5dfdd40c7815ae08628ebea975d4112bafeacc18b59218b28db02cc0de5 +size 70778880 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..408c9a08fbd90cb18bcb6e38b82677d23f75b4b1 --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbdc6415e0ac51a9514a6a24c824213038f56e225f7de5692426b4b08289b0d1 +size 141557760 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..e82098aa1375126008c44263d9ab7ddd0faa9437 --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2e68808d891786904319ab6bcdffd9503259a36e18362ce56ae7e2e983d47f +size 17694720 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..f0960b4f3d315096b66c465e9a481a0c907951ef --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315674d0210a6737e96d45407136b7d50896d3e1e77850cea0a4a704d6c4cf95 +size 18350080 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f53f0c04357abd7b089634fc7e45a4a9d1f62c2 --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03ede78f509ce77f4c2c4e63e420622804018c284423e3690db9acd1e52af48 +size 25921536 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..14b6228d90cb0d7dac7e2aa5e4ac6bfb9cf29f15 --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e03d38cdb52bfceec8bb8a1b88b5739c38c84d6eff996d6fa28f5759a7f52f6 +size 70778880 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..26c4d29bfff849d3470b48a735fc036d3cdae0b6 --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c0198c6c604f007b72888e8bd77e5eab4c876a1d6832e7a49849756779d5624 +size 141557760 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..61a7471d89e58f831e3543f92d905d3e2df486af --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dcd872a84189ff9f54ec6a0851fdde717143d97f4a4e3236b33c974669a0e3b +size 141557760 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1da149148a02ca1de3582a88a0eec7bec10b960 --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e11d1ef64caf61ea410f97f16ab94db78a4ab3d20351cfe37ff530ce4ab6b67 +size 17694720 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ac021d107d5af8b79613a26e2422d71af6c9adb --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6979e134ef044d32635f011e830f24685f2b92ea7d5d7a4d57c1810b610a27 +size 18350080 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..6492141d1e926197d7223ee417bd069ad0010378 --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3121ce48b9fffc24cdfc8eddaf9673dfb24de48f5f27199473eab94e1b525d +size 25921536 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..267d02e5bc0d0031226958709917d33a062d1d3b --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5bc7ba764ed74935cf0ae066250ce6cf89ce75aff609cae1c6fb4761620abeb +size 70778880 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..a88082b26795abb7fb1f274a350bcddf06b78bdd --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff1300419d5aac380b27aea2a865def3ed3d875a2b6d1d94d13cf228ff2dbbc +size 141557760 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..2b51f552c668d0879948d45aa85a4dbdb498ee7d --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a327747c1761c0cc68f1ff649d8be4ae952ee664793061163a320588ba8f5e8 +size 17694720 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..31ed77f53056567283b7b2220cf0825646856ef6 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce13e9e48005974d17b4cf66fcf2af384b683fe56429f1ced68d37912a83136 +size 18350080 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..ffce16c1c462c04ebb4a3fe5d921872edda2c2e6 --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4908dc3bb1a7ce514ac53b6e75941ff87d5f485e5c752ce248dcba03103d2f4 +size 25921536 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..bcc9ca8aba94522ebea1e5b04cb82e1249a39b7c --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ba7087d1fbaadc049b3120efe54753260fcbc49979937451f26a6da76d06d7 +size 70778880 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..da08491a98042d37b569490fa3d1f010a89c3c20 --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5aa5ab22235334de4b8f46fb1d9741599c51dbcde98417f903c22229927c4d0 +size 141557760 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6b1b5bf6a848b9693ab3c1591ac3fbe985f3c3b --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2e319eac652482adf02576d793dc60205aa2b4120d712e1e408db556ff43b22 +size 389283840 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..89e41c5322ad2da55d1773520626d0057af42c67 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eecc20e88639d8f7e6212222fb332c01d386b6912cc93dea5824e4c24d4f6c8 +size 17694720 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..a781970fcef56d68f3999a8eb1dfbc419a86d5e4 --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22dec9da90769574fd4721ed09cd08cbcbd1b70a328422e5a1ee5b0a4d8f296e +size 17694720 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..c266b44a5c1f3f445cbd62a06e4ed00358568187 --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb5a5d12c27bed38739aafe26b9547b583dda59855d2066f42d0c668b0866c3 +size 18350080 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1d407fc476e42e647c9a0055a3bbe6f038e67a3 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6336dd5c862f4785f03c8556ca02cca5f5805a18c54f03bab862d051400bba28 +size 25921536 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..807aa201a0cced4d1d05eb3015a83a2a9c077c3e --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0484215f7d8b3bb1df36b874f783e13b14f869b8753856238c6092ad2efe56 +size 70778880 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea3fb6dca83d070815d91eaef545615f8e2c746e --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95400be0c71a04a6f07ab1f005fddc83e0cf378f5670726aaeef743956e28b6e +size 141557760 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..58b26311b18252e2f3b474096526434bc8f06544 --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d7bd82d715dc1139614b679cfd9e01d9fda1776492a233bf3aab63b5f8f285 +size 17694720 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..1173e8257e3060d2c631553a7cca05a713183aaf --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20a021b2f591145ffb19a798e3b070f9841a90280a4beae7ce21592590bb93a +size 18350080 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d50aae53d63e6e31a95e952a0fa55bbec73d0c6 --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f727bcbf4d843fdbe4ee1bb7339c2e57384dfce9e4540333634263895de998 +size 25921536 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..bbb54ee81f0c950745173e16ca91d151f1507ce8 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78165bbf5615946f3f2b8b9d47aa6667bc9fefc446698bae60845c35bba1d55 +size 70778880 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..07ec579870e85f3c99c80384a7eb63a838fd93e3 --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:627dfc7079f0511cddbc57562571c0c9432f1854230d44ba6f7ddc6dfa8ef84b +size 141557760 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..e23e0cb23aecafe62ecf504d53c99c6eda4afa41 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ccbc250c765b941966a79911b59961a566a6ebbac6437336227fb54244d6be7 +size 18350080 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..080d1447d1c036aeb67b5fee7878adf0c7b6c844 --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe9e74ae675535c3351292d0b634cc5cd0ec00681d608386567c418d1dad8c3 +size 17694720 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..7952abb8ba9da820c6e1db32c9e0d435e2b95e79 --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa1f03104a0537626c98b249fd057f5d62c79a51373cfb7a9316dbcd392b97c +size 18350080 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c62349d0e3b47661d8acf5c0a50166f5453d86c --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd38dc6feef2a2f7bb48eedc0d56ee54524bd01581add122951a9ce1654e93fb +size 25921536 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..4dd641403ec5b97c131425997be8d0d8a1c42b74 --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d330059794a079cb4fa4b1337ee61ae4fb0b33eef3c4754a826a79b0a42fab99 +size 70778880 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9aff5ad15e71487dcdc92227fa7c6edb639c453 --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ee17642b38b58a75be01a61cc7f754988fc955d6e03265ec6d0ac8bd0bc322 +size 141557760 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..29b059699b303609d07c811d5ba4a61f3f067f16 --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:430ef08a7054f97dabda70d47510a61d258b8ab31f3dfdac50e6f3e35f4f70b5 +size 17694720 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..ad5c0e64b84e00545bd0af855b0a5e5c14059e4b --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba52038fd408492b2f7142231ad3304305e48820bfe9489cf358b54ea05c47c +size 18350080 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..75b24c1b2cc6559403f32aee8cacb69e868ca49c --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b8f1bcc839ea9ecbf54f28ca58fef13215ec1874b0353c2e8edd0036080c28 +size 25921536 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..5b412af608134bc7b017ae593bb292e0ce99ea42 --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df992b94b21cb0c0a4acf5618ee6af211ec30468fb541853eb70d12f28b93550 +size 70778880 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..3efd66a8c2176776ebbb597d9327b585d1f2cdba --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94dc60cadbb1a111545708ea8130c9e49d93ca97d9c586e3530d125f12721c04 +size 141557760 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..b99dc42a0d3cbdf99a3a5a529b7cf811775f5e3c --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ed200cc4a73508ae0bc3ec19dee752e52b86f1b79688afd22ac2458712a067 +size 25921536 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1a7297f4d09a886e0fcaefdbb6cabe6bd5dff2d --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2436af6d514bc07fdb3b07d0d7e3e0cd2624ec41765afeb45306837b9a889b7a +size 17694720 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..b43712d22ec59a425bc737e96502ab90e53c3949 --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22fd63b8beeefdbdaf77756a7d910903dbbde94679705480f3e08edde630521 +size 18350080 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e397605b82a504924289b884b654773c76386af --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff3df2b08cac854e7938e4559a970207116eac1773634807b226650fc70b99f +size 25921536 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..663ffc9c80ce442901c95294e86ebf981f999a3c --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b670efe1c1d48933f1fbab7e6f531eca0502bfc98b85a6f8f0718911c9bc1c6a +size 70778880 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..39774fa77a1b9daab6737902bf8465261e041dfd --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b6185f6bf605d0f54b99a2a29f0a84d31f5033178cbd7359a675b8420a4e5e +size 141557760 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..b15983d52cb2524a851d38ae3994b9d20e20c170 --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617a348cdb0657b1681435e201788598bd2f1b669a959e7269e598caa18a161a +size 17694720 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..67ec4f7d9931133f48985dde761fcf1c82976d6c --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b455642b2920106b48c6ff61798652ab7512a90679089363a1e250b244cb014 +size 18350080 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..14de85a5e584faf04e46043caf2d5c21586575b0 --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e71d76f2d95d9a67c63c524138f9acc40f684d7db013bec5c29a37608a71fa +size 25921536 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd62b9d8b44c34228c85a6d25123311b5678f003 --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:450c3166c5e526030ed63a028dd8c3d0e1aaeb892b4c68f9dd0ae646ebff0557 +size 70778880 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..0c9f2685e9613c7b739dad20f91aef28f832f9fa --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174f84dbaf97c288c47a90b64c79ec4fba404e5836e69c06e4638f48fc7a02b1 +size 141557760 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..21695b7a293f53ec67a8010ed98ab16d0b082fa1 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6baa3509b7acbc354ae4965cf053c9e8b27b88916fccd39caa12850723d8e01f +size 70778880 diff --git a/params_shard_230.bin b/params_shard_230.bin new file mode 100644 index 0000000000000000000000000000000000000000..e965a6b165cc0989463179a7052f4be5a39225c6 --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6ce669550fe16dc961fea7b62c1859b18f64ae3e9e242a27d0d19fc8108b22 +size 17694720 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..44494e655c852d3023cf30626a5d697408526f5f --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d5973a852195488963307c47b820c525b47e5fef816200a43bcc8b025396cd4 +size 18350080 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd1e5c05c08e8fafec986d3478232b99787c3bbc --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc82da410e685fcf79e813c00356478ce005c122a89dfea188b89316b9962fc +size 25921536 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..73f4d390a158f2efcbbf0308036396c3363342d5 --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03526a6e6fbab4ec81dee5d828672ea139267e3ca00771d1b0945cf055b40fe5 +size 70778880 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..c555d7c96867d8ab5c48d91b4c1876d4d7f8f0a1 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a9665e6f4f8e28cc4eeb46ed8bac6c4b20a34b3cd1713c36da5ed2586bffaf +size 141557760 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..aab8404e44c3d6c947d509ba95e4358c7c25700f --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7654da8620148647399f9b88aea95f51b0760582fc741989be6c78ab9a1f435c +size 17694720 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d9a990b920e3da6decf8c9553309482f6a123b7 --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9bf279a794fa05972837812240d91edf0dc58621baa4fae6e3b70f98558b38 +size 18350080 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..33f28ea9f5758544b66cebf17ebd8a138a71c7d4 --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af310da7462fd83d96268cf10e9aa2d576aff004fd5a81ab7a504b87f922b7c5 +size 25921536 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..e8adb063112565aeccbe31073c43f62ec82af752 --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4585f3683b1696ce5079b94e39d62b3b6ca9f426f3fe523212574b27437004ea +size 70778880 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd05e63033211b08ed3f7aa85916521e34dc1e07 --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641e294796e376b4f358783a9413bac5903cfcaa1bb325fcb7f0cb7df9a6e175 +size 141557760 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..5b2f2f02f3a23a3aaed7d52595cdda068e033376 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03304a493d146b46d27a1219f7d0db93a1df3d258d2c3ae0c1c9a42fb9d45785 +size 141557760 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f7bfd74e49cd62a1545618c26415e25166a4b34 --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc9d2bd5282dfc1bf6b0a49ec2de927da37fe9f2f52a594eba9e4286d17e721 +size 17694720 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..e566e52784e06a69d7dbcb906ae1b246b4ab895f --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718eeeffe25c6e7f3243655b2858a7495ff9afcbab94533e70b6bef0f3940a0d +size 18350080 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d4dba612a54ec251b16050c0c7de73cf957d264 --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd071aa98c6d5a04143d0c8ab2df173d5f494e487e5773113f1afca002ab79a3 +size 25921536 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe474ac1b74bdac7ad29d5d6f232848fd25e1df0 --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54b9c38096d167d8b8f3b5aabfdccf8739880b99653d62a36ebb36bcc21f9a3 +size 70778880 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..bcad67c44f5015aa37b75ce041de2124c139bf0d --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6179a154e192a7be76738f08db2df625f8bc703a4bbfd701814bbbcc12dd79 +size 141557760 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..c82c88a984a1dab5ab13437aa0713d14b2d99a81 --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4efbab5b5981af8f820994bf27864d36beef4aa5bf1784573648f60482afb879 +size 17694720 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..34377a96453f5c1a3de7c644e1433d1cc6795c0a --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7296573f7ff206de083b3341ebc44bf033154e841cbe95882b813044ce9855 +size 18350080 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..a107084b612330df78d29c00082471b042f93b45 --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273f3a7cd4e0c9fb233f0cac1f829fdd8ec62cab7abda92a0cda0a5f419cb405 +size 25921536 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5c76ce6af02738cbb3a8b055921d86ef7cdef35 --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aba0ebb14393eafe5278c74baaa814f97a2c095e1afc18548a0a6ad25cedea4 +size 70778880 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a6b7feacb17f7601ccfeb83713dca772b73b7a7 --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d9d6e7d4974ebe1dac0e5c13699bacb9d8ad92391ce9569495d31fb717378e +size 141557760 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f70e9e59bea81bdd243a9ea944c28686ad3690b --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fbca151116bf110f4de6533a5080dcfc69d8c5fa5b1ae0528e0a9239102339 +size 17694720 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..dcfe1cc6e2292e24b2c6efd02ff7d5447f08224a --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fec906a5eb920e0ffed94254f13a7d223cadfbc128e98d9b1c27ae28099954e +size 17694720 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe0348eea7e52a5e7ec6a6d5b2f4cbdc70ac6667 --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16248981b445cf898dcbccd1a800d16ea5d17ca04ccc7730f5baea7c394e10fb +size 18350080 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..af981fb395c815fea0ae26e148fc3c9ced83a646 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a300ae994b4cc05b19d4e13667d269681a80d9f90a54955752c6e83a49b9e03 +size 25921536 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b09dd294d1bc4e86b4355cd280d3f3533f076c5 --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737bf09cd975bed34821ea9f3b32561a101ec869eb15e7e052333e99878e9b08 +size 70778880 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..e80be7a2bfb5e4bf5ac0a35fa6dcf06c81788da0 --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b41701a794f84c44b9dee838af2a63b8835eb0691db225fcb9cc263d2b7958c +size 141557760 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ad2438bc9a9036ea0fa0cfd0090359970ae7aca --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f734c7b92cf03cdcf21c36cca746fd87ac1e8316c3b160fddc9e228490e85ad6 +size 17694720 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..8dfa58e27d9c920d96b7d21da595a6a524c97074 --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999ea898eb3665e829e9762cbdd9957aea962332c48d4d5c67bab795c5c580f9 +size 18350080 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ad9ce64de47578291ea6b99f851e2f07e55bbb3 --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796dbd13b6fa8eb7ed8ddb8e9501561c6a20ccb930719dac00de30363a517be4 +size 25921536 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6a621e700ca68ff36b3ef1156173fac0da019ea --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e46be424cda6c296a9520676707cbc06d8ea010a4a46bba3b522c9e714af5a +size 70778880 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..8de70fd520bcdbae7f2bf51755eb9a6bfe2e0573 --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d39166b56e217ef97cde3b4a6d333e672be029d4863bf4a52067820599ee12b +size 141557760 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac547dfc49d12e92b8785f356991f10602285e4c --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eeb13b4c34cbf86b017999550ced48412797b8bca576e6d7873119a31f5b008 +size 18350080 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6268b5082b5c567121945ba24a4001a61547c17 --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922695cf71f8ec63d4bc837467226d3a56d5562e76f9be52a8a2a5a836d4eddc +size 17694720 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..a31ab0e5d1fba7bbadb8f1d48f4537aba42457b7 --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a877a1f8b47bd8e42d74add2c1696c26a60bb6ca7884d21e812f49bb5081c0ed +size 18350080 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..194986e256b89f72c4db763c13e0d4137a9ec355 --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa545b7291ecc271deb149beb1111bbaf5d601751dd61a862e3b1a20aeeadddb +size 25921536 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a3d0ed9bea4f3d6258b6adf1205a6221795aa7b --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ee32db8b47feecdc0b273464e271d0e4e4dffbfe2987e37a02dc9c7b977868 +size 70778880 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..2885df7e78fdddd78641598ebcd5140e829cc2a0 --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400553b87698124abcf90ef68b29609f0457dc26d3b21297a71807c177c6122d +size 141557760 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ea7869c304b005606ec2384b5cc4da1d7c2a382 --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cacaceaee3a02dc481a51066aa77fdf07f650b2a394871b87d02e66a70b3f7 +size 17694720 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc8c68ef119abc03783d05cd26d75051c4df96fc --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e31a77893c71bee952e1d7456590ff94b68f529efb47be30587e78cc08d47f +size 18350080 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..3535ab456c42960b4a5c892ac47d05edbdd2319b --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7f82940c1c717f4476f91b1ab02e1320956de168dc032bb4571989c8839ce5 +size 25921536 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..08db68dcf275435c0b7887939d7aeea779777f8e --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66d71dbdc3631fbcbd4e38d217275fa3bf47f97879cc8563f299aba3a06bf7f +size 70778880 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..97516691d5bc3868710df2272e9bf70b9497a7de --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:021311206d000ceb6467c97d720b4275f2b86017e00c325f6bbfce05dd4bc12d +size 141557760 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..6cadd48f36e5977f66c678bea62e3054735587c2 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40c1bee707b9db286ec53416acf58abe26adb22a10d5ffee76172ecc27265c6 +size 25921536 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..42e9038162f5a10df968d1be12d9777100185739 --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82f3f50c6149b4b0aec1b87cff135b49d24e95b4ad7f48ea3450aa5ec604123 +size 17694720 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..74572df4ca467999825392e0eb3a5f30d47bed30 --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e501776d2e7ffc52526ef7c741b759f87501976a4dd1c352a446826cf807e5 +size 18350080 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..15a2d23121cd43c9b6d034e74c1796ecf0eec4ab --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64aabf71b5424f5a7b4724d0fc069e112170fd9b3f67c4797e4f0c26d259115f +size 25921536 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..812ca0d11b21008d3b2ff70cb77ac9e03d3359aa --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b021ccb487d4d6b7474fde44758d97e914b307394db76ec39b817ae2427a18 +size 70778880 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e746aa68867d1164cb81ef436e7ab16cdbcbdef --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35b325d9cd42b1235efbb6d91c6ed3f014d610340b7d210211d2b705bcfa461 +size 141557760 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..f53efc4218accd91a90ad37dbfaa826b3dfe13e6 --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5891f84fed5e428d01cb725d6520d6a591395a9366e011601f71f8a52a909b +size 17694720 diff --git a/params_shard_276.bin b/params_shard_276.bin new file mode 100644 index 0000000000000000000000000000000000000000..83c0c7eeda023bdc99e9a4d1fabd461707cbf451 --- /dev/null +++ b/params_shard_276.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369d3f110e0a358604d7e28324447b791fa684aeb714090db774381850d45003 +size 18350080 diff --git a/params_shard_277.bin b/params_shard_277.bin new file mode 100644 index 0000000000000000000000000000000000000000..dcad48cf357b43d4b6be1f2180d0e6c5d844c329 --- /dev/null +++ b/params_shard_277.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580faebd246cbdf5787672f95fe801cb0b660c02fbe22fda27e949b391f5e916 +size 25921536 diff --git a/params_shard_278.bin b/params_shard_278.bin new file mode 100644 index 0000000000000000000000000000000000000000..860e4905ced1ec8d4487f6e9efe16fc018c78966 --- /dev/null +++ b/params_shard_278.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef69e044611f890ead83a196c8a4cb3ba93d4576965241f4898cdc80e873e1e +size 70778880 diff --git a/params_shard_279.bin b/params_shard_279.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7dcd74074a0430f340b4ec923277a6d50b23810 --- /dev/null +++ b/params_shard_279.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cf187ff9773764ff0aeb3fc81d58175740a2b3ad732c4c74d7cd0490c8bbfec +size 141557760 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..f66003fc26fa85a738b7878020e065a1594769fe --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4a99d524d72f77713b696396fc857d32a2b7cc67e64a7546cead48dda0f3a4 +size 70778880 diff --git a/params_shard_280.bin b/params_shard_280.bin new file mode 100644 index 0000000000000000000000000000000000000000..c2d941704483cd2902b03d64464d99084adabf2f --- /dev/null +++ b/params_shard_280.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51825a18cfaea8c8d747bd7cda8f22dcf88b24ccce1aec19997819cfa77fcada +size 17694720 diff --git a/params_shard_281.bin b/params_shard_281.bin new file mode 100644 index 0000000000000000000000000000000000000000..468bdf858f7de27f6c29f26c3f0482562ef028ce --- /dev/null +++ b/params_shard_281.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd5321fcd44ab1a37bb26bf8ace793d23d1fc65911f4777a2f1edd37f00f5e7c +size 18350080 diff --git a/params_shard_282.bin b/params_shard_282.bin new file mode 100644 index 0000000000000000000000000000000000000000..91b53952379a9dab4fbf4f0868966123dce48052 --- /dev/null +++ b/params_shard_282.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428c02ca23e78880364d36d7c62348615671519406d3bf072623d14729ff13f8 +size 25921536 diff --git a/params_shard_283.bin b/params_shard_283.bin new file mode 100644 index 0000000000000000000000000000000000000000..1350da344852603a4ad4017ac9051d0df2253bf0 --- /dev/null +++ b/params_shard_283.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542599ef3793b17db0ec1a15aeff182e0a2d9465c13a629f14d3c08e329eae31 +size 70778880 diff --git a/params_shard_284.bin b/params_shard_284.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f6ecce3f05d760b1a4250c4fb26abb08a6b1c31 --- /dev/null +++ b/params_shard_284.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddacf8d0907cdfb3584c42c3e706519baa39030a3b55e729d82c41e03d77c4d +size 141557760 diff --git a/params_shard_285.bin b/params_shard_285.bin new file mode 100644 index 0000000000000000000000000000000000000000..771e85e3d187d7958af86a3d08ef85fa49e34756 --- /dev/null +++ b/params_shard_285.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d432e2f2f3729165587c9f4d897ed8c662218c35fe89e6e2e3ae31977d4a6e +size 17694720 diff --git a/params_shard_286.bin b/params_shard_286.bin new file mode 100644 index 0000000000000000000000000000000000000000..4593593197aecfd9b12ff18461d3172c758ee957 --- /dev/null +++ b/params_shard_286.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07aab7891d579e6fc84613960a4e6c56c1f4f7d6f83533e131f407ca6bc03fc +size 18350080 diff --git a/params_shard_287.bin b/params_shard_287.bin new file mode 100644 index 0000000000000000000000000000000000000000..46cbe9ab221c699217cfea829605d769400ff52d --- /dev/null +++ b/params_shard_287.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9e2344749dc5eef3bf6ff16683a0756a21754e054b513ee24bde25a76f9ccd +size 25921536 diff --git a/params_shard_288.bin b/params_shard_288.bin new file mode 100644 index 0000000000000000000000000000000000000000..1cfe57bc470ace3074cdd3e827a7dad9c4f61b6a --- /dev/null +++ b/params_shard_288.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3c7edc2ceeb2e2d7143106c21ea045e5fd30b99df72582163ea2f4b7ad915f +size 70778880 diff --git a/params_shard_289.bin b/params_shard_289.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2bba658471f1a3159467edada8be63e2399b865 --- /dev/null +++ b/params_shard_289.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0379563f494110a523652b5a0399c7062ae71dd032509aca848f484d2765c2f4 +size 141557760 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..f159f17e7af716553aacb2d38c3b700fe73a0a4e --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb25065dc68c9fb3a3da33595f86d6b057a48e0e33f904f6e19a656f15ad4c7 +size 141557760 diff --git a/params_shard_290.bin b/params_shard_290.bin new file mode 100644 index 0000000000000000000000000000000000000000..9c6951a03030e20584127290f06c63a663252442 --- /dev/null +++ b/params_shard_290.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0146f090def1b94971b14bcf1a8fcfd1cfdf4e8ee5da7a02a1c3cba5cb4cf9 +size 17694720 diff --git a/params_shard_291.bin b/params_shard_291.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a93d2a0ee9087dcff26205d849f5b3b9193033f --- /dev/null +++ b/params_shard_291.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793bdfe65a94753ecdaefd76767dadfad21910a26e73f496f3106e783afd3617 +size 18350080 diff --git a/params_shard_292.bin b/params_shard_292.bin new file mode 100644 index 0000000000000000000000000000000000000000..490ea4ba82ee534b4c11271e705008338b356c61 --- /dev/null +++ b/params_shard_292.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e84e2d14b31e3ae0d59ba3649bf882293b11ec5375f60308fb1643b34b5b137 +size 25921536 diff --git a/params_shard_293.bin b/params_shard_293.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a5d75e9edd89d3feee3dbe2a0e6a424a9d73e29 --- /dev/null +++ b/params_shard_293.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7bc12db70165faadb1ed4ce95639ec8e96a3912d7c04305104990b3cd2061ce +size 70778880 diff --git a/params_shard_294.bin b/params_shard_294.bin new file mode 100644 index 0000000000000000000000000000000000000000..6044e81fdc009b3d4daa5234be609d3003078c65 --- /dev/null +++ b/params_shard_294.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34097008d2f4fc6391f8b98a1690996e3b43ffc605eea0f92c65c6029e68121 +size 141557760 diff --git a/params_shard_295.bin b/params_shard_295.bin new file mode 100644 index 0000000000000000000000000000000000000000..2bb942f585dc81266a2f7a22e37764dfe88565c1 --- /dev/null +++ b/params_shard_295.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0171f353bca7cdff5d2d509559d1a3e268c5247c5bd29d3c415be715657518ad +size 17694720 diff --git a/params_shard_296.bin b/params_shard_296.bin new file mode 100644 index 0000000000000000000000000000000000000000..66f088dc47c90f81ffc23cf9398bbad9561401c6 --- /dev/null +++ b/params_shard_296.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eccd38367bf3627767c3b9ac192186730c5158658bdfa5f4ab9dfc8f9d5d615 +size 18350080 diff --git a/params_shard_297.bin b/params_shard_297.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c3749d127ce5d13e9856add07366f58d9c36ebf --- /dev/null +++ b/params_shard_297.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:117de9a8d86c6b2759889fed9282dae298bc360c1ca24846a4687664514f6fb2 +size 25921536 diff --git a/params_shard_298.bin b/params_shard_298.bin new file mode 100644 index 0000000000000000000000000000000000000000..849231f01961f7a0fccc8c366b5c2ac9208602c3 --- /dev/null +++ b/params_shard_298.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedeca8ec697cb0808a3ac524cb6678e8815988c30c5f606d9f309f879e01f4a +size 70778880 diff --git a/params_shard_299.bin b/params_shard_299.bin new file mode 100644 index 0000000000000000000000000000000000000000..f51366774bead1c5550242e21e59d2304d240092 --- /dev/null +++ b/params_shard_299.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c09bf5ecab6848a3062a352176dbe365b9d23f24682b2250db8a9074d2d92b42 +size 141557760 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..f303d9892671c8948b5d973b960829d70513fd9a --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b1f3a6c5bdde6038fc7f10fb6e1341639e75d90a7e577967b6163a73bf8b35 +size 48660480 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..89a4b5d69bb29791d634bf9b5e49561911745f2e --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fc33d53bd86d5bf0ff46ee117b8e93d741c19d1baead7f0b0b6263c0cf004e +size 17694720 diff --git a/params_shard_300.bin b/params_shard_300.bin new file mode 100644 index 0000000000000000000000000000000000000000..63117753447300c8fbb3defaac7d40750074ee76 --- /dev/null +++ b/params_shard_300.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe325ba837ac9071bc64e8dcfda035bfb735f4a84b94748a4166c50b78c29ed +size 17694720 diff --git a/params_shard_301.bin b/params_shard_301.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d84d15bf7de9fffb4136c0412f65182f7fe81dc --- /dev/null +++ b/params_shard_301.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bc469ed3ddfa5256fce5ba520180529af19f863beaf36d4453cff033e9f9eb +size 18350080 diff --git a/params_shard_302.bin b/params_shard_302.bin new file mode 100644 index 0000000000000000000000000000000000000000..89a1cdf2d031209581d9543f179943f1d865d6cd --- /dev/null +++ b/params_shard_302.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986f8f7a0b0ffd9b1c306ece3b6dcb6440174c34091ac8439e57e5fabc65027d +size 25921536 diff --git a/params_shard_303.bin b/params_shard_303.bin new file mode 100644 index 0000000000000000000000000000000000000000..29fd669d06b8f1ee45b18f20494abfdddcda9302 --- /dev/null +++ b/params_shard_303.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c25879c46fc248ac8c238baf06d7420f034b8348c5b19cb45ba8cccdc9c274 +size 70778880 diff --git a/params_shard_304.bin b/params_shard_304.bin new file mode 100644 index 0000000000000000000000000000000000000000..73fc9e8947c50d91f595b046281435f77eabe80d --- /dev/null +++ b/params_shard_304.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47e467dab59e69e0612362b0859d935db742a70997ace7db53f101d7966c7c3 +size 141557760 diff --git a/params_shard_305.bin b/params_shard_305.bin new file mode 100644 index 0000000000000000000000000000000000000000..2687112d4c65ea6efd5c8033e746436f3c82e1fc --- /dev/null +++ b/params_shard_305.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c836eef3d23e82549c603c1658ba4a539a4a11c03d141cae8711d7f9a33e9a09 +size 17694720 diff --git a/params_shard_306.bin b/params_shard_306.bin new file mode 100644 index 0000000000000000000000000000000000000000..4e8e4c1058c94c689effdf827aa88a49d8d1d8a6 --- /dev/null +++ b/params_shard_306.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c67213c18d13b20f7f99a8ce414c733166d579e697ea1628a44412c693af116e +size 18350080 diff --git a/params_shard_307.bin b/params_shard_307.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e12835cac97d70f694f7955dbd73c01e4de470a --- /dev/null +++ b/params_shard_307.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03bd7aea395f2133b02ab1f6d29ecb03c586a94abbc0090706ec74f036dada97 +size 25921536 diff --git a/params_shard_308.bin b/params_shard_308.bin new file mode 100644 index 0000000000000000000000000000000000000000..96ca90ee8d839beb3811e425da57c13224a757ea --- /dev/null +++ b/params_shard_308.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac98b4b9a4e75b1068ea0a9d92d030a35cea49cbed085b99b5330440b494287 +size 70778880 diff --git a/params_shard_309.bin b/params_shard_309.bin new file mode 100644 index 0000000000000000000000000000000000000000..e88b2ed72bc286cdbf9917f665f7360f12450792 --- /dev/null +++ b/params_shard_309.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b38b0dab0c9f8568c5f97abfa3b9d5da31404fb5b934bcf0ac23607926d45b +size 141557760 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..41749009f8afc8546d29fd8417ad339e5e677d6f --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e91fb0fa4c5572211d0e2ab666f9f8c2185b00c77b6b42be78e714955d05942 +size 18350080 diff --git a/params_shard_310.bin b/params_shard_310.bin new file mode 100644 index 0000000000000000000000000000000000000000..35b61e3214e56c988a53c60dba60126d50ba9b9f --- /dev/null +++ b/params_shard_310.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae983fde41e8d285ab1fbc5a50d534f2cbbe6738eff5fee7e470d75c71da52d0 +size 17694720 diff --git a/params_shard_311.bin b/params_shard_311.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b1bf74d8d898b6134e9f1fbe222dcea842c7ec9 --- /dev/null +++ b/params_shard_311.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1da538e674a339eca71ee4d6316474239f9913afdd6fd144d61a6dd15b8a7f +size 18350080 diff --git a/params_shard_312.bin b/params_shard_312.bin new file mode 100644 index 0000000000000000000000000000000000000000..624f04f6873a6f11671b9cacdd58a31e8ed98626 --- /dev/null +++ b/params_shard_312.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33fdc8727863e5b35ae60b34cbe38f7bc0c2aa0b6a96c8c9442664b6c67d17f +size 25921536 diff --git a/params_shard_313.bin b/params_shard_313.bin new file mode 100644 index 0000000000000000000000000000000000000000..70e00dce646696b8386dbdac3a7cc03ba2e7dd8d --- /dev/null +++ b/params_shard_313.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f98ce127175d24ea3264876ca91628e26166ff4a9bd10e7680402d029d4d38 +size 70778880 diff --git a/params_shard_314.bin b/params_shard_314.bin new file mode 100644 index 0000000000000000000000000000000000000000..d8b7dd4f30c177a321e48db2a1fce83ecce55c5c --- /dev/null +++ b/params_shard_314.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389f0ca39ed4cc53b8c1dcb7b0043290f836a500db54f2c7768ee36b862f7d64 +size 141557760 diff --git a/params_shard_315.bin b/params_shard_315.bin new file mode 100644 index 0000000000000000000000000000000000000000..5cb778127d0f14ba6a61f5daad398293155e52d1 --- /dev/null +++ b/params_shard_315.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c76f4caaadc149d8a7ab27729b0e4f2a0c0dd118d3c7e44ad824790b18d99380 +size 17694720 diff --git a/params_shard_316.bin b/params_shard_316.bin new file mode 100644 index 0000000000000000000000000000000000000000..a60bb64999ee93cb9c80f8031c3dc2ecf8af6ef2 --- /dev/null +++ b/params_shard_316.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3128658656102be828ddb78f6ad4d300d5a628ba1462eed228882655d8b9a8 +size 18350080 diff --git a/params_shard_317.bin b/params_shard_317.bin new file mode 100644 index 0000000000000000000000000000000000000000..c457fe698996409ee0f17ca1d258704c83fc58e1 --- /dev/null +++ b/params_shard_317.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9bd680ca59b01094347d67202b9521580ead9b96a1fa448249563650d85a4c +size 25921536 diff --git a/params_shard_318.bin b/params_shard_318.bin new file mode 100644 index 0000000000000000000000000000000000000000..c539476d97a19eb271f6c414bc993e7057872752 --- /dev/null +++ b/params_shard_318.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c398eb741ac9b444587eadb089ad14af5cb3f1509cb2260d497ca3c4642ae18 +size 70778880 diff --git a/params_shard_319.bin b/params_shard_319.bin new file mode 100644 index 0000000000000000000000000000000000000000..370191795513495af0890b177c5a4449fd57840c --- /dev/null +++ b/params_shard_319.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334271ee2cb575e3ff632f0fb40dd6bff2cbeaf139b63c8e0acb4884c137bb4a +size 141557760 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5e979a774ba7ac01291fb7f8e336c23f781f212 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b86c3c45091232aaa3e3404b45400d505106768fac4ed4ee1d8c944899a99cf6 +size 25921536 diff --git a/params_shard_320.bin b/params_shard_320.bin new file mode 100644 index 0000000000000000000000000000000000000000..91be708e0fb8ccdb3113a0f4f0683cf7870352d4 --- /dev/null +++ b/params_shard_320.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656f2dcd941f488192a8422a37ea8f121e86775dde4c94d98709834353bf4a6a +size 17694720 diff --git a/params_shard_321.bin b/params_shard_321.bin new file mode 100644 index 0000000000000000000000000000000000000000..319ca8fe4861ca3f97ca8f548e6f4f0284a52775 --- /dev/null +++ b/params_shard_321.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebb05416e08512d89bfa24e683e7a4b3dc8a28ed3a926636bea8403f5954e92 +size 18350080 diff --git a/params_shard_322.bin b/params_shard_322.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd5e457c1dad5fdaf400b0dce5a0058762746e68 --- /dev/null +++ b/params_shard_322.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd830fa8ab7e9abc6a784653679d965d53efbb2a367e249dbd5f5a8074d54084 +size 25921536 diff --git a/params_shard_323.bin b/params_shard_323.bin new file mode 100644 index 0000000000000000000000000000000000000000..a54234df2a4530166fbd3d3a2b00f30181dac008 --- /dev/null +++ b/params_shard_323.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b89c46fa76cf41640ca6fdecf5d07c5cea4c65df47fb3d11bc87969ca0f8f5 +size 14755840 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..51074a55e9b6e5957648ad6afafde441d47005fc --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20eb444a884236664aab285cbf7db6c49467ccba6ae903d1e3b5f29712b8f615 +size 70778880 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..15037160c3c03a5c705189930eb4594938dfcc79 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe72d0110355f4a1c1c4d18edea506224f594a5419e83794c913c22a8ce9f27 +size 141557760 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1c73433d12743965e75fbef5273ee9d29c90dad --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652c972c3fa7791f9060911d6faaf778b978da360d9dc1808a114863543113cc +size 17694720 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e47fffd69d7b3decea8bb8acc8b5d410d68a781 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ba9eb1ed3e33d2eb1ceb99a978d321578c8d99bea39d72e34dc383ae821a08 +size 18350080 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..04689008bf934de827bf56e95dddc59ed468efa8 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb2bf99d341474fe906aca332b2513068f335101c244e7b0f510283baf65e8b +size 25921536 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..a96e0ff06fce5f7ea681d11f1bd41cfbceb3d9fa --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a866dbcb72c1c1f022c26493ae168a1638e06d3864b02f06bb7401897409e99c +size 70778880 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd4d3591800641e56b5968a00702dfcb83e4cad5 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6834e9b50a702d8dbb6fb3b185d4f71153316ff48120d59ae1d25cf3514f3b5c +size 141557760 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..c0a29772002c28826222efb05d91015b4b677e73 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce3dfc0890047c71c177b00be3017de08d79ca99bdd2777ca54068129cbdc83 +size 70778880 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..a00c9fdd9118f3e53f5c134cb00421dbbf1c244a --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d701b7b7cafbc7971d9b30a514f7da45d559165539b1d5427af21fe5399c32 +size 17694720 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..21eb8382121dcd5d4db6e07bec79188dbf1deeef --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29251f46cdd7f495960f6be5e329e7efb56a0659c78c2f884620b09bbcd784e +size 18350080 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..913339c89e285e4253ea58c555afd54318045d44 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8290411acf703e6993041777dd60ab5b2d4ddb4475be8325056d11f6e1aa08a3 +size 25921536 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..125bcfc307eba9f41ee501bfa4697deba89fbbae --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8369b6f7efe3f96f1ade4162f8c8247f9291a91ff4950eafcdb4da045cf69e +size 70778880 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c1cac584e383cba27ac138e49e0e234b12c6317 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353aa611ffbc79334849c851ce3e128ec4692601cb40f9214dbc91ddc282ce37 +size 141557760 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..632b7519c432c8bd6a57c288f9d6aaed98d970cc --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41db2e9f873ffc0eb20550a2d768904e6b624e07a101f0a42181c6d6e636f26 +size 17694720 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..57e3cf7e3efc31f873d4847f36b00dd16b954a55 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714ee36000e351318a37588f4a94e5251e193fe7ef51af25cda751c69ede57e5 +size 18350080 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2cdb6bbbc1875674338c95df17790f07d06fc5a --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14dbc7151ecb7f17c2facbb8a3c73e01432513797559f7429e06c9312df54ad8 +size 25921536 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..54683690552a30d42891b8a60ce6a0a25c6ebce8 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b7a94bc706b3c040cf8051a54c4ce6f6ebd8c1d273aa16861aa562db2daf2d +size 70778880 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..8002829b7ea404a93b30b9d8a26a19de62979396 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e68d52318cfacca7df2cde585af03ceb47a532fa525266d6779a5a507d82b4e +size 141557760 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..160813c2a03f4e1415f37edcdfcdef909f4561f3 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0074c50ca1b4922eecef480e18ee0ed3759bd9950abb8e5c2c7c9cd7c1a25664 +size 141557760 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..81c327022051b9f86152ae0d273b89fc3f31693f --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8398bf42be18a9516fe9cf897dcff641a3b88337bea0150047606f666e8b19f +size 17694720 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..816afb8fc4c47411ca3bdd3533e9394216fcaf75 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ba68fd6c6da6b39f4f06a2ff237318b6f362ae54fd6b2c82ffd8a94504f97e +size 18350080 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..578c168df513a48676328bc08a4323d31b99f2d6 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe7aefc39e6288ccb41fbd12cee1ae58af5595838fc3d1b1427c682ed5acb30 +size 25921536 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6e5caaea75a6ba669a927c3c1de453862f5d5b1 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c724f1d473efb773fb1d23727296da49903ead2926ff4aa721f8d27a447ad0df +size 70778880 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..551b62787238739fc90110d8494a84f657661ffe --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea22c0bb855e45596a0557044cabeb04eb9d1d4bd861c7058be5f4ca39bcbe0 +size 141557760 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea7de8739e4a6debd5ab39ab7404a2b080ece561 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2179f012910c5607e57817a764157e247e0762026c25665e08c5c9db782f8d44 +size 17694720 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a66111983a6c15060ef851b8007efb82e3d4275 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49afbdbce30caba1ac59169c72c836ad5bbeb92022ced8db44132e7feb54812f +size 18350080 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d8b3d5cd7163766414a7a4c5e9698ee32afef7d --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1768473c84d8f6ba27bde3be7e22019dec163ae05eac04cb053b0d06bf5bf09 +size 25921536 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd0f156717ff89750c5835366a9e73781daf8424 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf449a313d2a4b62aab4728bfe546fecd802306636493fad052df70b08c943f3 +size 70778880 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce62b2b03a9365bc8edd664edd4939b2ef205056 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec441225340ea971512c573e18b2903f6c41e59b4919a49d353b8a2b6fe0d9d +size 141557760 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0415e1b6f5fad05948c74b8de4e76ba6847ed14 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e635288420fa627bcc67d6fa0f551504e1783a51eb284b38ec2c90821021a3d +size 18350080 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0dea7d0cf1fb9ffc200e6dec9fdeeb7eedf0c44 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c450e407e696567ddbe07c7d677602284235fde55e03fdb6ed97adebf5cfa6 +size 17694720 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..230c9d803a270fe1b7e996ca32175841f3645bec --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fda4e4269372a432513c4f243cc81b87a27e183d6ad501c63b3eb7d73c167f1 +size 18350080 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..d65480be86e75f1d2cacf6776bd2eb7bf98b5a96 --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74ca0e08dada8649fb45a4bda4b7eb303f4efcffd1f85a181fcf09fefa4b982 +size 25921536 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..da49d2cd5f10d04b35814a0b6d652cda6b089a31 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db25124259be546c04391306e2e9992ffa6e2e38748a9c93c6b84891fd1e61be +size 70778880 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..4e98d1bdfdc6532009df70f4e63e663d62f36a44 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f6f8fd56edfd0b07affdde7ecc89a0f34b69028dd6015b61d10cb6748b39f0 +size 141557760 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..dde753cfbeb71bcd53a3a1eee44232d71f162bd9 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7673cad49c8831d5964e5a9e1cf8bb4b9beedcec74b7c08e1fa40d5d8137210a +size 17694720 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc1cce4ee2c12f0629521fae9a9fed21631650ad --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9edba7b97cce042b46665da12a3d37f4f613ad000af22aa1440b4807759fef +size 18350080 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6f8ffdd7926bb393c0df48c4b280b33a29734d7 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ebb59d1721745b1d33a173ea530329f062b3dcc9987bf92237ec6c683d23b0 +size 25921536 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f3c18849c9a3472d2c320ed5ea683502326c221 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef88a4455a5bc660367cccec519dee84da7a486a8473fe03ef9dfc13d3ba12e8 +size 70778880 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecb5d70d49a09e642a40478a372ab94bbad55577 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087a1c2afcecc96a43d519b5d39890dfd9a348e1a27776f135d2203400238cdf +size 141557760 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa151dd6f3f682243b4bad4a2c89953a7edc47c0 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ce43b6cc8fcc04a76cff4e98972e7eb13afa5c53e596588aa8edd68d701edb +size 28870656 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..64a3530579fa321bb40e8e141646585f983fd7e7 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a210e212f237a8cfed08066ab45ac706cbc4af4defd1717c3eba787bff8c92 +size 17694720 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..52e138f6eacc33dcb6993738838e90fefe5d21e3 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6473ca639fd6481d8c73f254e1cd548c0907169804464bac02229a997f5382 +size 18350080 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1544a0777fe741e3d8c025bcbfe8c0607e3d9ed --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b696e2a8a98041a3b0aac45b8475e3baa9f4203cbb426091a60088d45ac8cbe +size 25921536 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..cca27451bb3b687b9dad6fe16448fb867ba8c6ad --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d82dbe1777aae0b35b6004e996b4c164ac0e371137b21f4e5998b98263482c +size 70778880 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd41cd3bce1a74290e4c14e237b8d5b761fc889a --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:439f4fa75a1b8c09793b62a14b5b7d592d0cb5615c5c096909c0d7216a16eabc +size 141557760 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..5803b1086eeb81c9299f1c929b8e3541be0d0fe4 --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0a0083af27d7a4d77d35095cc8db6e2ed3548b503907953105682e86e96966 +size 17694720 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..74c59e2c2270166d03626e18e8e589e7b69f97c9 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d77768f7865b8f9e7034c1be9d5ec9aa1b4cf2515a02b72ea4da6f13f6b49e +size 18350080 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..58207a00b18bf4d4d5fa41e90ea9f0862fbad031 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b8849510c3422559650a6c4f7a24f7e6f07c59fc7f19ece7acd75c7e068266 +size 25921536 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d63c58ebe2d41ffdcc70d9201970884b8dcdcb3 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77cdc0690634aea48df65cc30cb974e422bb5dad0c9ba0c294b5c72b494f9fa +size 70778880 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..a074b48531b04c2ee34f5f500d7f9fa58a2832e9 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65852b1263f2e235dd1a99398d48e98af4e1a98ad35c0d5e5edc798c98c18cc +size 141557760 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..3851a8a46d426189cbbfaafd1727ab2b4ede2107 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:921941ad7cc87510684e77c4092e38754c183f85752b535fd3719c1d828a6093 +size 70778880 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd76e6ce0ad3bda294536665595f564f23605abe --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a93c45d37a1be02929710c1b3d69b5bedf0917e62a48df864929338adbfbd0 +size 17694720 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..f560210ad5b58e408e33704b8508095f473dc085 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570ad443352b4b2afac239b38563706bc0b248d2a0366f9b532062d493ccfc8b +size 18350080 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a4df6cdb9f058d6ed6cf3033a2055f74d7ffb50 --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1670f3d95f070f4d26f10977f5059f4f697bbe44d1f1c5f16a89fb1ec126f42 +size 25921536 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e7ed8e5c05f6a78628704292a373ea581e6bba0 --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580ec2c88d8a1f777aeddd719b0a4440f34878a43e89cbd1ae4dd9be1cbc8cb9 +size 70778880 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..cad1b91c6fdfd5d8b192867e088126dc7fc7785a --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfb529dece56fa8c458e83c09fea6c43f68233e9ce449da4a8d2ad865d8607a +size 141557760 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..99c0b62e622f14399c82fae11123725d74a9a62c --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789220d66a53a33afe9a50e4c411ddbf7353d0f931a66caf5ed3f03bae7f348e +size 17694720 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..4df51bd846dd947e0828d8216fc9db95f96d4def --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef90ed7398e500ebbeddaf0f3e4a6b10b2f50c918a61c9ce23a4adcfe5f1a2d +size 18350080 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..12dbd8f5bdcd98917837a94c04fc688fd311d326 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064f00ac07a9bea9d49e50f16d5dce0a4126300ebc3091ae183732b342b195d0 +size 25921536 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..f62cccf6cda08c873c2f160b3bd8a6bcd3d060c3 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e575b154913c3798313fbc6f6ae4274430e29da1969b3aeff3f0b86acc26c8d2 +size 70778880 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c4493a6b52d6c50aefea9f0c5448933b235f2cc --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7997bc36bca15a454d42fade7b812adb7609d71cfda59f4f6d604abba07111da +size 141557760 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..bbb470ead5dc9debd972920e2732321df54539c3 --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70b178e87ab8d515605ebb35e5aa78e36decbcc12cb02e74b9208f7824765848 +size 141557760 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..9cee77d8fe4ab1e06ccd3268a8bec2e839cf248b --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abaa3cb12641da3def3c63824f01e8382f2c81433466689ca46f95e78c637bb7 +size 17694720 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0bb455123a9e8dbd2f012c34667cb42d0959646 --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc79994e67b02c5c9afa50d2188e23027de6542559c0f5e091726da9f3df5f8a +size 18350080 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..864270bdba0e5df7d1f6645918797c737967fd1f --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a41ae3261c17e699ccff1a8e58b60c56af92ac77caf365635c87d4216d3359 +size 25921536 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..005b0185d4a9a34037d02ffdf23319ddc1cd2cb1 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d832cb715ffb2e979a796a3302af32dd6cdbfcb0cfabe1c559a9e4a14d1158 +size 70778880 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..254b7ef4bee79a486ff3e422f740d73c2bced74d --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b3a3e1501740699841bb449f1437c3881bbd848c06c54deca3a32d8d18e601 +size 141557760 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb910eebb5e2d060f82e7d5871c1094522027dac --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73318babe0ace07e5328c43df910ce55116317fe6a5d0b0f4c2f1cfc8339aa1a +size 17694720 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9791c590a2a39427921f1989c0290dedf77d734 --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4ca151546916dc46466c83e3a9c49eb4cec7a315e0a4235c3d971de30b5d39 +size 18350080 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..a20cf346f84dfeb8868269e9dcbb475f49a7bc04 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4729966e25befd2e2d4d07109aa8fb8cc7fcebd1ff1ad4dfc3f7fcf2385c5cf +size 25921536 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5cd12fbbaf6b5b743815230db4d1f983dc58771 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4dd71a813c752c2e11d5a5bccce3437b3dd09ef0e17f06e9187a0f8a6d4a1a4 +size 70778880 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..f931c0a6ed24b9e04f9f63e1d81a3855d4334804 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a967163acedd19fb71dfcb1d1266b38393c4c23e3cc93e4150576877cddccbd6 +size 141557760