{ "metadata": { "ParamSize": 195, "ParamBytes": 16060522496.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 1050673152, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 128256, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1050673152, "byteOffset": 0 } ], "md5sum": "7ebae45530fc0d893e3e82d42202db1a" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ca8c3ad5d558e1f9eb313475f0a56b1c" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "95204c97884f67ac6f27bafa00e5a0f7" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "00b817e72533ae68bbcb3d2809c0a060" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5887d7f2d363e66d65316c1c0602e44e" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "e4c6f9979cabd4afa237436c1116d142" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b6c056a08f32cd354799fb495a501c01" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "61f1e1041541251e1b566f870efae8cc" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cb7cbf9fefc15ab4ee92a2844cb51af5" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "0787780e8fbc38943d4e71f3fa0e5176" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ecd915e4928aeed6a61e8892ef4daa6d" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3d4ea2b168d8caa2c0f16fb848dd69cb" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ad0925f56271df7f72c95a7aa4cfe5e4" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "7fa766a308a37473cb1f014f3294dae7" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "80995c966656ae76f2810fa3b856859d" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f0cf602a515742188547154c7b96dda0" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "555424de782a031fdb9aba6a16ef51a0" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "54cb03c4e7b57d36465f3c214e2cfd2a" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "909d53920a474e2bd9497212729d4e0e" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4bc6a3f05299234b660050b6856a2bc8" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c71cdad13a900958d5f9180f49e5ba0f" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "5a7d2478b68c9bab431f74b3b1b84314" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d4a4761a585e87c6a8deba46cb61ecdd" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ef07ef723d978343e3d4a7f903596e14" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "687c00e9a2a5001fbc76effd91bf01bc" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "27ff2b2a8fbf55cccce89023f43b0a70" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ef8e1e9e2d86ddfca9318bec90333582" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7d5c1062f5a5e583b61c611a4680abd2" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cce955c36aa076400372d35663093e44" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "62cf13677a51166b430024f2126d33c6" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "625695cad6d58c6bd73bedd1acb2f5d6" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "229859b20e864356aa3136228bf86ce2" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "838179a4fd51c7bbf051911a7c82c1ea" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "51d9d581449541c99cb688ffe6e208df" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1b808e983bb6f2a11d7281bfa04ab0ce" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9cb14468de5231ef8dc4921d0b1cd457" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6a9693a00f4929253e6b320afdb6e87e" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "641829e342e78472cd1525ad3b82079d" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5c3a11f4d0b6489e93213ea2985e684d" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0012180a7b582eb088d931123c524ac8" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2db6796bf7796101a1d164823782fcc5" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "0d4ff959bad1fb1036062fd33a2b653f" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4e552f47f60ff94b5ea0d86260201693" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "392fe8dfa2b74d62b63b42f4166e17ed" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ef06ba4236730d01be89cd1f71c84c8b" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "268cb60810301305bf74fb537dcddc19" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "295eec56f5e3f72e5287eeca538c02ad" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c94c0de9ceec618aa41b48362bb5b6a9" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bc738aaa38461a1a2930b5ecca15a220" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3c29179ed243d165b3f4aa4c96dc18ba" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "96368bebd12f0f380ab9628725f5ef16" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "85bf529b2398b126181e380eff1ca756" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7993d6adc6a1e118e91a1185e1a6be0e" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "dc7eca934b48ccdc332b13ee72093047" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b279ebd65f22b73b964223407c37beb8" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e431b6ca2662f811eb829db316a3a38c" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "03c002bf0f2e762468f4ce52027580f9" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "bfb25cbb289ef59576d48afbb12704e6" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "53f1900796337b4ad09c7357efb9301a" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "844a0546733b9e9fc84c0bac72ed2366" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f82e60c5088c1431c4015d993fc0db89" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3625c03b41bd48c6ef120d3981030acd" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b28a7708b7b06f537e12e85980fe4ced" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5c538515aeb0c8a526f7ffc8cc9032d6" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "eac64d8b2d9f56318dc7b05d39742e77" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6d6fbeeaa5edae719d82faf5051e75c1" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3dcd8048da86b5b40d8677014d0511c5" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9b74eba8046a2b7e104f728c3db84340" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d06773284fd5c2773b78e8ddc0d56bc9" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fd4daf341618a5a72abfa7f571967022" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1a01e44970e9e0d7e56956e8e2c065d9" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d74777c65ca70f4a054d3acd7d3e6c76" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8a3e43270a8d5149b5faa1355453720e" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "67e6cbec872561c10e616ba6b0935637" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5a16c51534ef5d2f3f8ae06d77d87bf8" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4392343395a0f3a7cf6fa7ac6bf04d8e" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cbb4759cb59e25429a049f1ebe411f3f" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3a16a973fcfa7635e0c40f5968c3e1de" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "356018c6015202553513abccacb485b4" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6bedbcb7d419d8c0020009e9a9b07e04" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5772b26e396f01846a74e6ca7a5c2f24" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "47a4e347f8d657041817c5831f01e91a" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2ef1f2dd028893ba805c0d24820cfb98" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "28dcb1fde5052e2cb22d33dffcbbb083" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c480425e803aae44af7b5469d715b970" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c1a51b02669cead70b8bcd4945a36463" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "65c8632fbf5fce6ffaa3aa8c2797d731" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b289a2822756f2b6164c672d96cb96e2" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "69ed6c6c5939d5b10ab29363390a3e72" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ee18cdf821f603cf776404c2faa61743" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f1c132246add3069d2e988fe861019d7" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0b971b6800dbd4010d5b4f7e8837ea1d" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "663008fdc444ab94cb5ccc29a48fe8c4" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ca9f2509003357870331dc2c5df6519e" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7d5e86e22bab8c51059c7a1141537cd6" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "37f98fa6afcf7ee46a38c4238905065f" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "970d20e1c1525169c912a5bd0ad85402" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "76cad6b61e53019d1f2112ddf917ec0e" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dc860c87229120f75017f159ad6d629a" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "66608fd85c802497e9dac03c84615609" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "dc4a636d579ef6faaf01de2108e93828" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "32c1d5a819b2413ca6350133f774b4ee" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0ee0588e97f8619967faa8e57bedc5bc" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "420930418ba9784a0848e287d460f635" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "574629021ac2a81addac1b30855610b0" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "8f6a42da990f745950824bb01a481c24" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "68ec616e50ab24ffa16620c56f64716e" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7abcbfd8e9736b73afe0787fa67b0a67" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "222d5f86f727ffcfa0c954057a45e0e6" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ed638a5714beff8901b062e82496ceff" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c1dcc5000fb3750f82a42c7bc875d2bc" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "40a3e9ce273b8a78453e91d649fd6071" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "10f9598b30f2eea47a658539fa64d02a" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "afcc1ab8cbe68d70d5c30b806708e484" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "54d07fe101b987403c9a3bdd55a6d079" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "feec1e5f98035d8b8e5f26f79ffe9f6c" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3a5b81df8e5e31d15219d8a7eda3abc6" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "eafefda3739d195131ddbcd579e2dc78" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2e81be609535fb4c210cdaccd873aecc" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "dcca30af585d09e1046b9e8347ac8f14" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f62f60717b8edc354fa25c4c7aeb7313" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "da165019befbcae2b2c5f463efc8ec20" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6b096b7e4ad64d9d9442342be4f7a907" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "03250a5a2f935912e1409b9ded47bebd" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "973b59ad1d25bc399adc90d188fa3cdc" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "cbb585d4c647cd1f5b04e0669eb3f3f6" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dd38738aebe2b9c431efa8e8c6e3958e" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f6388aedbb6543cfae4af100f7e55544" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3690038932e6340e98a214b4d5ba9d2e" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 1050673152, "records": [ { "name": "lm_head.weight", "shape": [ 128256, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1050673152, "byteOffset": 0 } ], "md5sum": "3aa120cd479038b2540e9d22e6e70f00" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 532480, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8192 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 16384 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24576 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32768 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 40960 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 49152 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 57344 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 65536 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 73728 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 81920 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 90112 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 98304 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 106496 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 114688 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 122880 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 131072 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 139264 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 147456 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 155648 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 163840 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 172032 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 180224 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 188416 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 196608 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 204800 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 212992 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 221184 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 229376 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 237568 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 245760 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 253952 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 262144 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 270336 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 278528 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 286720 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 294912 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 303104 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 311296 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 319488 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 327680 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 335872 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 344064 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 352256 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 360448 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 368640 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 376832 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 385024 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 393216 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 401408 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 409600 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 417792 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 425984 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 434176 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 442368 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 450560 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 458752 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 466944 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 475136 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 483328 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 491520 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 499712 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 507904 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 516096 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 524288 } ], "md5sum": "c762118a1f8ac666b38f68eb8f49017f" } ] }