{ "metadata": { "ParamSize": 170, "ParamBytes": 12850999296.0, "BitsPerParam": 32.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 788004864, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 128256, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 788004864, "byteOffset": 0 } ], "md5sum": "133c0866b77e2e5678be91a753bb7e28" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "93080db9b85b8252e1138672b9902f9a" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "0c18f71e770e7c7c07270f2d7ec06d1c" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "44251b37a994062bedadfcd599328de2" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "bf00d477f6d478010a9c7584c93723fd" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "23a00478c5789710e44b2229f5b1f0ea" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c15617b1ce4de0ecc8e85d8566d4fd07" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "7926239d43547e6b686b15951a3a84e7" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "2237119d8791ce2a58941361b80fa84d" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "d70ec745e1feafbb4a1d86914adfca38" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "75f3e0d41780aa8602f46b1016314c05" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "90f3ce08908231682aa92f2c1296e5fc" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "8e2ea40c1f92cbb61b9d658895140b07" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "083ec2e27ba602a63ebb32ce85aff2db" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "94dd82b511ec123317e8ece8285765af" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "75fc3f6b90b60616d2696b12412fc23b" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "1f5e4e0701c74744048f742778298f61" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "91108c2df99c4b9b87f27edc7c75d600" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a8abdbceeb4dd058614f3f144a77ece2" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "c75eab31f6da7c631a17e2ce852cf003" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c6dbd24e7eb2d5485a7fa009326ca523" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "ce2e8339c0cb6d4457a5ede2b3bee0b5" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "611b51469fd096b07a9463d8f2a664eb" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "50dc7e6b1fbee76eaa87ce0f5ec3fcc0" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c6f7f3faeaef9e79991b7d94b25ee011" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "815b14c6b06f48a87b5adc0cca956cfd" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0916f5bed827fa16ce1ebe9c089097d4" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "9ddd05a218bf06c0868f80bd0b270eda" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "9e02113405c9b93e9eecb883f1db14d5" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "303e6706d5782c66c3a11756ee513dbb" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "59c43454b5e413cbaab867a90ef827f3" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "f148aa81afde44c61e15ad4ddf01c8a9" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c1bc09fcd5aedc98f925795d44bd597a" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "d75aa45200b65bc44500abb95e9efdcc" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "d2607a22d2aaa52916e1f99977674d3c" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "6b0bc187e174276f9068c71f001861af" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f29349e71e3c7cc0c5172fb8de9e637f" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "b98a90817c9fdb702470209e341ddd5c" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "56b6d3ede5ea23c9994fb02c48a82cd7" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "f6c60380deb7a8afbed11b307b145e18" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "088c2b1caad88b346fbb5a3cb0d45110" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "44d02bd8483c1a0941af26e32438bb55" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "824146de15eb8206b9e7531a3a068b6f" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "ad1677d7e01e4ef22f342607f16f02df" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3143003000df5244f9fcfda00b62e2a0" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "96d5a23e28e0cd687ee129bf25bdd674" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e7445744de4fce67eecd628cb5955f42" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "4e8a3a848bc7c572129bde24545e91ab" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c0d47846f1f268c6b9d034420139e267" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "ff5c419b4b570dfa26fe530cd0602a75" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c11179f8247d6d4c364971a6450740a4" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "7588e5e7fa4304beb826fcaa6f3b3e65" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "49d7128811effec28ba14cd181946cb9" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b2559fc7223d8081ea4ff1f38efe170d" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "427dbed3aa91d806dfcb213501ac507e" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c86c1149c905eeca37abb6ace6b65081" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "d0270175e869b30212326d8898f6bc6e" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "97edc380dd2ad36b07b1dc01832a4407" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "517ca02bf6261842f24247640bc0903f" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "7ae5988d6a252fc160f8afec618d78f8" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "31d045e4bc48359a0a9355a6b1227faa" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2499d76e5b76de9a57ee472ec90d7385" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "75c244d8197b1919723016fa125500b5" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "33c9ea14ac77d2ece67498ce22af6419" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "5f901b9695815d535efed5b0a4a1e931" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "d7806491318f8baaf9769a0bded6dc0b" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "7d60368414ca9cab75b2ae03b15fb208" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3052bcd3ac2b8d80ef17287f901bb3b9" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "c511a17ee7127ea3514af602b5b5f75e" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e6e79670e5e719b3cec1e97f318218df" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "90bb59b9defd080833ae995f838e39fc" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6f7406fcbbaf37055796ee5282acd5e8" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "d976299fe65efbcda8040d0bb0cdcff4" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "1fcb92f405a175f578814f4f4c1ad88a" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "71663fa01f184a407c2a5e19ec85e9e7" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "4e9ba681099e252c6cd123007b45e416" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "e58dad56d1aa5aa3306cb3190ba7ff1f" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0001d2ba2d5eea1354aef2f5c727fe07" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "76f9235ba682cf5b0388c94cdef2ec15" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "5b7ac8c47930806d061094840999d5d7" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "02e74665c93354e4829fb04653abc27b" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ac1cff11d9b4cc142961891e4b0fb7de" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "67bbc168157c53d1a1a1ff8b6052eaa1" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "cef4f79d43d9eace1ad5c2bc0bbab32c" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "caa538f23db663ddb35a0f7613bced7a" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "ae2c3067f8024380c9729aeb23055920" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "80fa2ae93a50724674d3ccf3097bc110" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "8005bb547cfd8eed05260de00e01d305" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "55d1db437255049a98db5ca1d677dd25" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "e7f1f30f38670d683112ba5706a2f092" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "04a985de9da66349a9e0401546d9a065" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "65ecf4f35052edf63f9f3d20c470c5dd" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f0d1c8ba2a582fdcc0e5270f7c061471" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a0a933b90f40ea9b50fdcde46463cd55" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "da99b4fb689c104ee62ad2cad0cfa534" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "0208161744636162aaddd958458c42f4" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.24.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "1c87befe152239ad5a565da807630695" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "f9a41904bae1070952eabe69083f82d1" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "3aed6dd9398fa605f8c3539853ba96fa" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.24.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "6e3573ab844d10a115a672e5eb4101a1" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.25.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "1f0c9184fc17fa72a166b741fbd14304" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4e952489e44feff3f51f293243193963" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ac0f2806df1ac7868d2e83026271f057" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.25.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "81c614dbc2fac010a3809d3c51055227" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.26.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "028de1825559128df8e5fd233404f13c" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "91c6cc596728b4d45f07bf90e4ce40dc" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ef94f2bf8dd5bcbca41d8c1cdf0a9208" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.26.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "403dbf175a8c9eec0e8f94d700500be8" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.27.mlp.down_proj.weight", "shape": [ 3072, 8192 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "d7db1850f8f194d48ce5fca0cb8aaf7d" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.weight", "shape": [ 16384, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "d970e24d360046aada8fa036e74a0104" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "71d768ddcd341542e6b40db9ae197d46" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 18874368, "records": [ { "name": "model.layers.27.self_attn.o_proj.weight", "shape": [ 3072, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 18874368, "byteOffset": 0 } ], "md5sum": "bf42c4b4af143df9f6def1800dd32225" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 31807488, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 6144 }, { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 5120, 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 12288 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31469568 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31475712 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31481856 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31488000 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31494144 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31500288 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31506432 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31512576 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31518720 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31524864 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31531008 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31537152 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31543296 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31549440 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31555584 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31561728 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31567872 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31574016 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31580160 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31586304 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31592448 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31598592 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31604736 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31610880 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31617024 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31623168 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31629312 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31635456 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31641600 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31647744 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31653888 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31660032 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31666176 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31672320 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31678464 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31684608 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31690752 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31696896 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31703040 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31709184 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31715328 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31721472 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31727616 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31733760 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31739904 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31746048 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31752192 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31758336 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31764480 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31770624 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31776768 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31782912 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31789056 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31795200 }, { "name": "model.norm.weight", "shape": [ 3072 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 6144, "byteOffset": 31801344 } ], "md5sum": "8952ab985c888d6241e0e6204be82d7a" } ] }