{ "metadata": { "ParamSize": 313, "ParamBytes": 3927297024.0, "BitsPerParam": 4.12551973205239 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "ba597f5b8c2d3c11973ad98fc539528d" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "30ea8069b35ab462a8814bbaed167d95" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "c1b02d6065b460852171350e14e799b8" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 28 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8515584, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 8515584 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8524800 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 16782336 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17040384 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 23462912 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 23663616 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 25785344 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 26846208 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 26853376 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 26860544 } ], "md5sum": "d6554409f0b617dd14c5006badceee81" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "fda4387a874a71c25f6eafda47530d7d" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "16f9a815923afceb9ee1ab430bd11bae" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "9f3ee64202eb471e8a6d6ab26fa028ba" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33483776, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 8257536 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 8515584 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 14938112 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 15138816 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 17260544 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18321408 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18328576 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 18335744 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 18344960 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 26602496 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26860544 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 33283072 } ], "md5sum": "1fab88cfb15b23c4ecab4a3a585309c0" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "b6abd4423853df63cc64a3fd2bf9d771" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "c6e25bf448d5e946bab70cc6c13d6f8f" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "18b6ac9563876ee4c58b0d5b3a17b462" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 30066688, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 2121728 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3182592 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3189760 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 3196928 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 3206144 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 11463680 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 11721728 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 18144256 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 18344960 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 20466688 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21527552 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21534720 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 21541888 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21551104 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 29808640 } ], "md5sum": "78bb60f5cccd3863bedd8518bce0bb36" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1d1c2a467346774994845e640e2baa81" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "c02e52e26198c309014dca3ad639191b" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "3ce36b1d30e37bc550654ac91a61ac3f" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "aed4753d00524dee7528053018c453cf" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28174336, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 6422528 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 6623232 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 8744960 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9805824 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9812992 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 9820160 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 9829376 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 18086912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 18344960 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 24767488 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 24968192 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 27089920 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28150784 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28157952 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 28165120 } ], "md5sum": "f00205dabc5fce40af9f3e0e1ad51d38" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "318505a8d0a5cc6c4230ba7a60eae636" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "7f3f27eab5d89578988f617199f1b8a8" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "d4bc2bde93e2d8e18434535a86d81059" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 33483776, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 8257536 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 8515584 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 14938112 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 15138816 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 17260544 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18321408 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18328576 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 18335744 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 18344960 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 26602496 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26860544 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 33283072 } ], "md5sum": "c5ba58d2ce791ad90cdf2a5dda69a5e7" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "6642b72fb3fc06031c2b9fa97948aa64" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "2b7683a461f70f0573de5b5e3c07b216" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "001e159804e7067c5aaab12e90f15cae" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 30066688, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 0 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 2121728 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3182592 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3189760 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 3196928 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 3206144 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 11463680 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 11721728 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 18144256 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 18344960 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 20466688 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21527552 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21534720 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 21541888 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21551104 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 29808640 } ], "md5sum": "d7e48de44e6905e3f22b6b5862da2c57" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7d5b79cfb53c60ea6ccc5361503f9331" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "d0723a95c2297b0db457bcfd1b7ae50c" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "19a5386292cdedb9aeb4a6b792e2edbf" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "e217368a10773b7a939d366443112183" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 28174336, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 6422528 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 6623232 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 8744960 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9805824 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9812992 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 9820160 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 9829376 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 18086912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 18344960 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 24767488 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 24968192 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 27089920 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28150784 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28157952 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 28165120 } ], "md5sum": "d8ad08938a9ca79eb9d9a307aa01dcc8" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "4d3a2c6244cccca856900c8efa971410" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "37d80a00471a492af8b151debf8cd1c1" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "4538baa5a896f51c03dbf5f4d1fb2875" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33483776, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 8257536 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 8515584 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 14938112 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 15138816 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 17260544 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18321408 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18328576 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 18335744 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 18344960 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 26602496 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26860544 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 33283072 } ], "md5sum": "a152d8f59ffd151a5bdfee482e69c421" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "e12c55d07258169313a9904746e9ac70" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7212fcd424c2a700db118c12c8b06572" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "e12693644ee0195b572cfe8360e63414" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 30066688, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 2121728 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3182592 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3189760 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 3196928 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 3206144 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 11463680 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 11721728 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 18144256 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 18344960 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 20466688 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21527552 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21534720 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 21541888 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21551104 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 29808640 } ], "md5sum": "5102ff2c138f48fbf6e86f64e9944787" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7b03fb4b490e49becd91425021fb9c78" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "15f389e399c5d03f54f46438b3ac83d2" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "4ea7bb677ca905eeb81694ea917baa21" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "ee5e4a6d674f613d2942962005deb167" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 28174336, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 6422528 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 6623232 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 8744960 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9805824 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9812992 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 9820160 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 9829376 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 18086912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 18344960 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 24767488 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 24968192 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 27089920 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28150784 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28157952 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 28165120 } ], "md5sum": "2cfbcd22451aa3c570c4db7aacf0b440" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1365cc18cc5be44faa9c115e6de4ee6d" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "43439aeae99b058a8ce2e55924c21cdf" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1b425a599ff943451ab0760b205ecfda" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 33483776, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 8257536 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 8515584 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 14938112 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 15138816 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 17260544 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18321408 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18328576 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 18335744 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 18344960 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 26602496 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26860544 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 33283072 } ], "md5sum": "19305e2a4ef62e90423045e9a9aa3eb6" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "937d72142d376a837a0a0be0801678d5" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "3994b7a72473dc6e9d92e5fafbb0a5e5" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "449e5e7eaad20dca94699c31f30b0403" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 30066688, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 0 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 2121728 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3182592 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3189760 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 3196928 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 3206144 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 11463680 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 11721728 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 18144256 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 18344960 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 20466688 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21527552 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21534720 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 21541888 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21551104 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 29808640 } ], "md5sum": "5ce3a144da19bc65fa9f3b8b668dcc1c" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "5f907a54c9af1cb22f9b83252a36c7f5" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "fde8fac7a0d3f77c4efebd21d125b315" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "335a8fd7f1b94a46d779b38599cdbd29" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "9501adf25160bf30721e49f28695be80" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 28174336, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 6422528 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 6623232 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 8744960 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9805824 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9812992 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 9820160 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 9829376 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 18086912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 18344960 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 24767488 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 24968192 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 27089920 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28150784 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28157952 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 28165120 } ], "md5sum": "08e8e84c77d188fa459db7e14b7c94ad" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "e8da06a564e5597674277dc8e70f71ee" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "7669ee9e5c128137b7d9589d602e61d6" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "a4eff58ac0df1f649f071fd8d9caf2a5" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 33483776, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 8257536 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 8515584 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 14938112 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 15138816 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 17260544 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18321408 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18328576 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 18335744 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 18344960 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 26602496 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26860544 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 33283072 } ], "md5sum": "375ae51850f6300afd335d9b55c4d7a0" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "1c259ee4c406bf3c446b22687343e9b4" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "beb2d6b3c1f1e66fbb25c2ca2c3c6a9e" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "39afb5fce8e6a92c7d9b6ad76615666c" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 30066688, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 0 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 2121728 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3182592 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3189760 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 3196928 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 3206144 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 11463680 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 11721728 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 18144256 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 18344960 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 20466688 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21527552 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 21534720 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 21541888 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21551104 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 29808640 } ], "md5sum": "1ecec082ec9b1f09e45db368a17dd1c7" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "cb8bb330039a2d07735ac7a97fa0184b" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "58b2bfe9209535e7b83878a777c83236" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "54a9ba82a1c124bbd28590a4eb985607" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "4ba61d877eace6e2a280cbb2a76c96e0" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 28174336, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 6422528 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 6623232 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 8744960 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9805824 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 9812992 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 9820160 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 9829376 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 18086912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 18344960 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 24767488 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 24968192 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 27089920 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28150784 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 28157952 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 28165120 } ], "md5sum": "d9bb70df9345c2b18741827e18509e5e" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7e6611b8e54354e1e7152b4409fdab5b" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "214a6c46111837d3fb912da8d37a325e" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 448, 37888 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "d5b7fdd9fc0e97bd81ec61997ccca6db" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 33483776, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 8257536 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 8515584 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 14938112 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 15138816 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 17260544 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18321408 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 18328576 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 18335744 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 448, 4608 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 18344960 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 28, 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 258048, "byteOffset": 26602496 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 448, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26860544 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 28, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 200704, "byteOffset": 33283072 } ], "md5sum": "38946fc3dbabe5cb5e44a341c360edfa" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 2368, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "e930d77f082e7f5398bed9976e33846c" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "lm_head.q_weight", "shape": [ 448, 152064 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "220d903d32be5999946a01cb7d46dd73" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 11719680, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28, 37888 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2121728, "byteOffset": 0 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 148, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1060864, "byteOffset": 2121728 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3182592 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3189760 }, { "name": "model.norm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 3196928 }, { "name": "lm_head.q_scale", "shape": [ 28, 152064 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8515584, "byteOffset": 3204096 } ], "md5sum": "44074d88138a8040f33bec142f9a2757" } ] }