{ "metadata": { "ParamSize": 243, "ParamBytes": 24495626240.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 1342208000, "records": [ { "name": "lm_head.weight", "shape": [ 131075, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1342208000, "byteOffset": 0 } ], "md5sum": "99069fa4fcac7c3c4eb562e7431da12c" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 1342208000, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 131075, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1342208000, "byteOffset": 0 } ], "md5sum": "9a395de1f1274d6e8c0369eea6ad8cfd" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "ab534c267259c4251419edd404ce3067" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "f05e1e7875ffe9c070ec1914a3db2c15" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "55fdcf78b228f3c33b566c2ea021006a" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "13cc9412ffb91d0fd32b8709ea1888c7" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "be59050b96f0f8a480725fdad745a1c1" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "42eb522732d2698b87008c038d3e44b9" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9010d4096f5fe1b0b342bf3bae333be3" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bfec4c8a0f99faff5e055e85b862124a" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "10be03005de5d03e008925068dd78c94" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "e4e06b535da650ba9aef579f951d2bd6" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "330f2bef16c270a627ce0ccd0072be82" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "56356a1b24b44871c7190177f2aba272" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "950b86b29e9029bde46db0b63f6af70f" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "a375fd0cb07920a9b46f9a5dc1161798" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "b0b9865152229bf8192841a2ee1f0e27" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4e569500617072d5ecf32d5aeda40300" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "c33b751f4c871d45c3e18032d2990ed3" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "b9321ee5a29648d5387d58b65535cb39" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "0bd37f00a41df3430b86e9a3ead74866" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "814f9a6abd0f1e975e3a8efa85af25f7" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "be0f3208ae7bc3261ae1d1f84975522b" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "64428ba104f1f73c16e6440196cd3fb3" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "325b206f45701a4135dbf9e53b37a765" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "551a5b411796901532076b90e42e47d3" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "32935e0975343f7aa653d24e28033494" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "c6f187f79621c95e5df585a36b802298" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "6880591e51e5b7d5d0e624ecd6acb973" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4c054193235e87410d777ab0256fcf5d" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "54f0c22561d3605eab7c62346ce57f16" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "d6d880e3ae7ca29ff57db585b89287bf" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "b56197eae6e248bd1bc1fa9b6d73ca22" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "47ca2eaf1b33f722fb2c282b6773c951" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "ac9070bce075096f29c5992695194dfe" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "34ed6b15dc6a6ce5087153778e31114d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9b572477148a6786ae148f3bde209afa" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e29f416fb3e4dd386e7660e5596cc50d" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "2b22b0012a6d32e67c1f3bd66908e7fe" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "ec97ec75563bf073df3d2bdf99467478" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "03e229757e9fd786cef5e3e28d85e685" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "43c59a67c74924b2d432f44aa8c59cdd" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "857d133fce11f59d033cef97bdec3c86" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "f00a086d2aac926b2f26bcc52ec0e14e" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "0214879520e7ee7b2cbebdccb167b818" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "247dcaef11a840e089aec6e49e9b14c6" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "9641e662ac368b5fe4bad302f6cd32d9" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "e53e1cf0f5e18bb22d204d282d1c8e09" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "8968054253bca1ce0bebda31f3df0570" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "504dac71b13bd6492f632d6813bdf092" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "6dbc97dc52ab32b05fd0eff0f3e24938" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "9dd19363449eda6d69d708be469ee954" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "dbe779cc63cda8694e61c47d4d222709" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cae8b268cfe2968487194617718f99da" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "eb8284a7cb33ea3a815f5d812587c859" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "15f623a1d9cd878b4b1a0f9d45edf2cd" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "5a7c16abb4b1e2612db357d9ad7819e6" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cc9111b7e345103eee596601b682299c" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "8ee36aca22da0bf711104ffa5ef2661b" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "fc5add8833698b52eafa1e3e8092ee99" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "a1a89ce29953988689698d44eff5f40d" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "095e599e5759e154cef6493a0ecf4510" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "34b679c628c6e4910a8dc4736ce34458" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "924d4b7880a9f1a50261a9e045c7b695" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "28a54975ef5b8837313039762109fd03" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fa592f00fd063b4b01b3567ecfbba855" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "b2808a216e9b4e4a1ce2aeeca0f6422b" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "43ceb3b892bef9d1e422cd6ffb326da9" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9ad3beab82b9b95f5d5557c371850f70" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2cdb1ab0273322cf75465ea63a74a39a" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.24.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "a9614d11ab75257bcf8910f914b7b7e1" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "bce6e289e7b60cb8e45865af9c287a88" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "4519171b1f7f2a4a5ae5b6321debe359" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4437d4f79442d6cfedf6bf94c2263751" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.25.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "ad4e5c33b40fae3630f94aac444cc290" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "927eecd4d821e8127feb1e88ffb45823" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9a346eca344a3c266b68ba2180155e8b" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "604a56c8c472c3f4dacfb675f9154081" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.26.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "32cd51120d5334ddf8fcf1afbb0eea12" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "67abcc1c992d64db53884460c4b4237d" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "548f583b79dbd63f046df96e2c8c463e" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d2d6d1e1c91c5064625319c39cfd8253" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.27.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "3e79f0c441bb3a6a7be2018feea3d018" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "3b93eff920ab012279689006f889ab39" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "79b4649504057662b27e90218ccc5217" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a6cf2f415de70a10c413c1f5776c3d8e" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.28.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "6e74fdce34b696076f37b0c93817588c" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "d088a002dcb218e6cb7e711be0e9af3f" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "bfd97a92afa769fb4c981f7ef81124a0" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a8c3a0830edcd9ced6fc32dce4b2d485" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.29.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "9af50c102f4e4c7b639496313b6e6458" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "dbf374dc8b8f33ec8b561ff755baea1b" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "2eefcb7f75cb59a27d66ab7a6c912fe9" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4c27532c0fa5976b17483a101dcba92e" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "da0da915eee37f14fe96a21efd5efd37" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "ccc54373c3757de6d27a415b4f92618d" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "52ac5476d71b5103294fb610b70647f2" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0968f3de44cf25e379db12dff44bbdaf" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.30.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "32df357c9ed50eb5db745456336ecc76" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "ecc1b38954c30b3f89923a059444a8c9" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "398c91519fdcfe0adb62cf1c9467da7a" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a6ad5c8a0413efe28cd1065f3da9037b" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.31.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "1362974c0cf1f6e9087bac7139d06d63" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "d33fd224822d40217d00bffda28fed42" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "49b3146cd27f4608816194c11807fd47" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7deeb1f2e75a08b885ec19e3ca3d2aae" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.32.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "e63375d20ab55f8b3cd43300f5c3116e" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "3e46ecd2880254afe04a12b4270d515e" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "bd0353022310668ee256853d3245ca34" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a085e2b18e8f283b4f2702d306a14c7a" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.33.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "77e9c64889164201afdc2aeaa426e215" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "a5443f3e81d545fdb69f90f7a7add0d5" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9a613afc11b2e674f043d35c2b582bd5" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "24ed344d76b5ee83742b89cd0a6236f5" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.34.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "7215d51a5a43225193ab0f3bcc3a713b" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "eaaf25f50f7b2c4b6db5c2637bfcc3e2" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "8ec87a23f220b7758609d727f773b319" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "32d5dbfb78eb769b45c8fa04bdd81aba" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.35.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "c769a12e6c52bb79f124687fe327733a" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "19b95523cf2897ee6ec1f37777a92dbc" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "e4ace35cb54cce547907a6663501394a" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "396e24c659d62fb88a97f0062ec22677" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.36.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "56d4c12d23dcd533a9071de788cf092d" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "0ca77a7ad703c51296931fd05d71cbf3" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "352876412d39141b0f699b8d1e3f248e" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a4feec5f26271444b6496bd61451906b" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.37.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "841df337e2dead8f40a0ab3d9f21704a" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "0fdf87dcf7eaa93f6dcefad42a3b4917" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "cc8a675d889e91f50b2a4c6ac5d2c0fb" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "db73b0e2942e2f869cb39ab8a50dc0af" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.38.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "0aa7b690014d2dc0077955e9ed3b4da9" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "89f4ddced68af942c076bd12b075eabc" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9653d3092e4bd8e71329c215bc0cd5c4" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4eb4945cf04a5d0739e82be75d25c5a9" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.39.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "39927b53c07402e98d3818e44b7e578d" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "cdfb8098ed8fa7910600d6e10aa5cbdf" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "9c80933faf646dbf05b8ac3de616afbb" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "26618be67d380a086fd64de8132aa71e" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "730434ad17f6ad3e040cdefd41c16816" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "6766875d43bc5aa87e420a5ad1273c39" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "c1495ad21f89b6dea84be8e24222f6dc" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "19f3a9ca61f14ef26dc7c9db802968aa" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "952459d6d1eb1f8d845615d000171d65" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "5b04137fd3cb8432da79863e78beb48f" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "eec67d11bf9b9052aca333e57ae176a6" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c2e799f26a2f1308158c001b8ab3e7de" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "1682c38f5caa780146387609e35d8a56" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "f8e40ba610f3413b455177866e5ef7ee" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "776eaf9c5eeea4ff606ce05c6ded5852" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1bc0bb76f367663bdccc798d36d16d99" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "24364fc6822f8c1eb88eb56586d5f2ef" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "df141a1663880665917a692dac108ca4" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "cb2952671af6958fadb59e5eefbcb4ad" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "55d8fa7300e14afb383e3a523a71232b" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "189cd8db3928d765e967bb6775edcf23" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "958d2365c138224b6e89f3a05e1c1ad1" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "2c62315c2c6d5e10fe376d29233cd65d" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "85080ed6cf57691eab32cbbd914d7e65" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 146800640, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 5120, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 146800640, "byteOffset": 0 } ], "md5sum": "a2df400cea0bacd75ad6ce24d49dede7" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 293601280, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 28672, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 293601280, "byteOffset": 0 } ], "md5sum": "7af9cb9d0e524f5d5426651963761bcd" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 62914560, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 6144, 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 62914560, "byteOffset": 0 } ], "md5sum": "ab9bcb65731c58d4612155fdf8e218af" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 5120, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a0e62eada330dfd35a1b9b1aa9a2c2e8" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 829440, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 10240 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20480 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30720 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 40960 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 51200 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 61440 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 71680 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 81920 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 92160 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 102400 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 112640 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 122880 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 133120 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 143360 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 153600 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 163840 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 174080 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 184320 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 194560 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 204800 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 215040 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 225280 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 235520 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 245760 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 256000 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 266240 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 276480 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 286720 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 296960 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 307200 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 317440 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 327680 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 337920 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 348160 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 358400 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 368640 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 378880 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 389120 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 399360 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 409600 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 419840 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 430080 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 440320 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 450560 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 460800 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 471040 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 481280 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 491520 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 501760 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 512000 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 522240 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 532480 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 542720 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 552960 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 563200 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 573440 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 583680 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 593920 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 604160 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 614400 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 624640 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 634880 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 645120 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 655360 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 665600 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 675840 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 686080 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 696320 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 706560 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 716800 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 727040 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 737280 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 747520 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 757760 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 768000 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 778240 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 788480 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 798720 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 808960 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 819200 } ], "md5sum": "934fa561606420706ef04ec218ab7606" } ] }