{ "metadata": { "ParamSize": 805, "ParamBytes": 36381212672.0, "BitsPerParam": 3.4891900844756822 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "lm_head.q_weight", "shape": [ 1024, 128256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "9cbe5c3f12dbd5336194e44f69d0c81f" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c53a9dc128cc655d37a27ac3cecefed7" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "db12fbb97e95ba6ac23ec24bb333857e" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bc48dab4026f5b89c928da77700282fd" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "32b5cb5254761b3144a887aede04dcc8" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 31145984, "records": [ { "name": "lm_head.q_scale", "shape": [ 64, 128256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16416768, "byteOffset": 0 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 16416768 }, { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 16433152 }, { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 20103168 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27443200 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27459584 }, { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27475968 } ], "md5sum": "e5a268e87a77e2d6cffd114b2ad5ffa6" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b22002a80272267a6927c65409bf49f8" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "36078fe8939f02e7ed0ea9dd1c563148" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "55b13fe34a485371c2af20e39c41e9aa" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ea5a290f357d764832914640a6218d89" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "263a8340a45fc7d5ecb93e13e87a9c7b" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29835264, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16416768, "byteOffset": 9732096 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26148864 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 26165248 } ], "md5sum": "bcd77289f384b78854737dee5d10eba6" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f129e23712c7c2fdf35b0ab9e57137b3" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "649bbdde12909bd325350ff995ba010b" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3e87bd632f36dfd071e7144ddc871bff" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ac1c34e5c53911547f2f460b4e2d08a4" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "db751206406c07ae751e55037411cdd4" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5b5a522712826f549a7c8a649eb0d03f" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "08fccc4f752c5d61848a70bbe5ca308e" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e9351ed66c8f631c790744d55572626c" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "8369793e228d1051675f901201dc0e98" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d3178723d286d8216eaa2cbc366b2531" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f088da8f7f0f364b355eb7e714d77497" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1dc8017053013a4cd8f785dfe891b83b" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f23b85e2a52583b6eb1f6fe8b335ba09" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "de85641c78a21f1de99c2f7aff123c43" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4a68f3d261da474a47c5049b59c1cea4" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "79e63cff2a6bc2868337b282e47ff3d3" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7ddb757091189af8232cf282587c59da" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "42118e147f8fd54438448ca0ae28aa15" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5b26097246a5f419df722ac8fb14f8d9" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "975081c60336a7e130bef4730b822e89" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "024cdff4288e65e3992143ce6a90d2b4" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e991018b5087859d5c816cc5c9f6d77f" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b236a161973af092b932d2b50a799371" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "17ba33648bd2856d5b5c49b82178c5d0" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "906e11539b2b4b3960487eb76985ebde" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0cc1d444145400e40140fc0e9248c5f6" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "94541bc2b8a37cf334ba6bce293bfe79" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "898b56c053a70467b781ae643f269412" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6a66894bbe95011e85eabed80d22cd17" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6eb40e0c0555215c1291bed8a8fa43cb" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 32833536, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 23117824 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 30457856 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 31768576 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32817152 } ], "md5sum": "2f6e626bd560e5b7159c77ca7f15a417" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4e6b119ade9c02e1a8296614f316f4bd" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d2e1e92b4037090162d8b767b72b99e8" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "16d5430a7ab8ad63e56828ab9e75a6d3" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "59dfdd673aac8810bba90b59e483ba66" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "07eb84c72b8f88aa164a79fa760f5d31" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "198c664060f299eae9ab82a96360c5c1" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9a6c80b0a0bebb7b6ec4708efc2fc314" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 28147712, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11042816 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11059200 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11075584 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14745600 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22085632 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 22102016 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 23412736 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24461312 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24477696 } ], "md5sum": "1a5630490dd3cd8de333d4d635e5745f" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "572371795548f69a1120d0a1b76ff71d" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "21f5d0ec21c627bcd90aab08bf25a609" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2ba9414cc8a589fccad407d9fc200dfd" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1542a5c893053dcbe8160fc8368b6be7" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0ae81b20f0f0bebdfab4b75c54eda6ab" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d073ccd352029911e97b01ee92637e15" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6ceb386637eb30eb0915723ae7b8a1d4" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "dc4f6f348fc0c3f6bd42c45615a3625f" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12075008 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 12091392 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15761408 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "1601bb99a1e8dc2da68402cd8a2ca45f" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "30318a84b8697ff7acd1e08e197821d5" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cb4001c2b4b48fe19e329408cb9885e7" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "352f224943682175e67034b89e3662c0" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5223c2a740c854b5b95815d83237e1d6" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4e73b1739cbe0200c2c026ed1eac4354" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d0b26a6826fda5cf2357e3cda5eb6344" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5052ec0e534bab5c60682123bddd1775" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ca6ec1fcf1b76ed9dbc07565c3f99ff0" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "897e10cca0dbf7a7ff82f4b1dca023d8" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 28114944, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24444928 } ], "md5sum": "75cdceb8aec24b1b52923972ed00b175" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "49d4305cf1eb32fd94a6ec3ea54fa4c9" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "fb1246ddf800a41ca82a3c09deba4383" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7ddd29bc3bfbfc0bbf2f920a42b8ab2c" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3674f8257cd0cb615fab5ab322590baf" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d5cb56de2b1cd36fa12b1a63556d659e" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9da293192beba86ac247aa6c8d72ff65" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "515aab3fdbd0d8b8bd79f3ee5e6bfb2b" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d7a8ec7d9126e4638f5f6f3477077a65" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 32817152, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 7356416 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 8404992 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8421376 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12091392 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19431424 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 19447808 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20758528 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 21807104 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 25477120 } ], "md5sum": "f59d0b5f576bccab91b1dd31c97f4b57" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "989ea8f990dd159a837438d31f89bca8" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b47a907ad921357e12b1962a8bdcc42c" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "2567a058e7c5058b0b84bfc0a1978ba1" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "459ebad91d65cdc8d43755062ec39994" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ac236653b0007a5678b36a92913573b1" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4ddc04518c237ff124f27161d8963fb4" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "207af4c4e316cd2c5df9acf210646393" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c642fad94e813cb27b790d12a7e1de9e" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "74f5804843e92fb6bfa74c09b216acd8" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "399bba4062ca70a783d8d15c91a19555" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 29196288, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 1310720 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2375680 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2392064 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2408448 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6078464 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13418496 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 13434880 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14745600 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15794176 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 15810560 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 19480576 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26820608 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 26836992 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 28147712 } ], "md5sum": "90afa12e8507cac1813261d2c95d0880" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "de2c561bfb6d1e91125faa01cf27e589" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3622b9355b5c36e6155b95ad8a5e74da" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e26565d96d64b3e4a76def1df4f619c2" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5805db3da20578f88b3d9ef8f94c8f21" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6e8ecfbc59612dd34a72116bd9a60396" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8c179ba23c946f154f97dce1f7273868" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5f4dc07b7a364a56eacf90520db1abd0" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "59655bf9ea930c380238570d10afa628" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "48a2e81d601d5c0077133c39b0a18536" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 30490624, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9715712 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13402112 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 13418496 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17088512 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 24444928 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25755648 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26804224 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 26820608 } ], "md5sum": "6bb88add14272e9eb8649eef8b60a267" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "599ec56c9dc61ee343644b8b1f8d5a5b" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a2c9c165c3ff49a07e46a5afa9dab326" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4a5a63a6796cde6eac9bfc1125dea1ab" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "02981f4bbe678add1ec67e5f221d824f" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d86a4a7f1a85a6a8fd63c427f5d7bffc" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "29ba1d5d3cb77a39f158bf94224e391d" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "692df4b9c7dfaa69a70d3e59415aa83b" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "73f2d27ace9bf4a740b8d80a65e23b7e" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12075008 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 12091392 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15761408 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "5956f970662128d26c92882aa30936b6" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e317fc39a2b72aee5ba17e9c30093559" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "260ccafab3c414da9cacc412fedef932" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9c53dc3498f741f7708753ba40e8a12a" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "36c95889a247aa601a95da83d306a24b" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "aeb0138fe85b078edaf45d4656b32af0" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2848ba1ec75775592ebadfd63db7ce5f" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1c5e0f7b8e6ccaf4b99c712d9a5ddc44" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "560779f7ce6c12596a504a18659b0220" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bc7d6c8cbaefa416f475667e310732d6" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 28114944, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24444928 } ], "md5sum": "81815b10699a2159517e15913ff5b066" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0568af5a9309eea7c71fb88ed2502b2c" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5a0001a435bf37732e10cb8287d90df0" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6a49297c2d69a040689400d40ba0846c" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1c25144a180839015ba42f29acc41b77" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4a2719ca96c04a1a69420e1b3933fc84" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a56f1080099a55eb099d69a48d8067b5" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ae4faddaf5570ad8931f07626a261935" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ff6b06748a11029c24e1e573037f41cd" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 32817152, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 7356416 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 8404992 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8421376 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12091392 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19431424 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 19447808 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20758528 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 21807104 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 25477120 } ], "md5sum": "b020c65a356d897039e24ac8e5969021" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b6c1b9322c2163f628161f9e7306ad6c" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c3c6354de42f38096f4eb49ae4f0f748" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "28c2ef33711d608c6e410b235c3cfe2b" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8a5d569b32f48e038a48e4e067819614" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "007ad437cdfa8a7da4044a568b5bb062" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "66e5cf640b235d0698c11f7d667482ad" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "47a5f12bb7ca19cdc7c2fae009c0b69e" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9d55268a5f67a0b676c1086f3df817e9" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0bbb99db025d69ef2d6b2dc18ad319ce" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7d57e410f5cf3e5d536fe75739fd954a" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 29196288, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 1310720 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2375680 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2392064 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2408448 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6078464 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13418496 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 13434880 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14745600 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15794176 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 15810560 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 19480576 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26820608 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 26836992 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 28147712 } ], "md5sum": "92486cbf8d8fb179fe311f5f4a11bff1" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "20bdeac8b702b9db9b9cafd829bdad34" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2f33b5a7ed27fc4c4e177cad7cc39360" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2ae854ea48785b66a3b94aebdbd116b3" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1a519c0c92897e1860da17e12599be2c" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "98d5a63dd895aead31385d2c4cb8223d" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "31cff9ae9da920aba30bfbd7354f59a2" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c4ae755bdfaca9900729521d87e82a14" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "61d06c1a64e70430ac4cace4805c89b8" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ff58e4a7208b09efcd6c88c569ec5fc1" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 30490624, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9715712 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13402112 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 13418496 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 17088512 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 24444928 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25755648 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26804224 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 26820608 } ], "md5sum": "a4b69d9b280fdd4c7f1157e4262c097e" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "64ba0bf41c6c68a810df001923767eec" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "77aa9023e1e81750a7a3acc3d397524e" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "488c146f8c25ca044ca7fec0d94fc252" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5081e568840eb7dc5a5f75f2ae17352d" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a07784cbf100a79c63d65d855dfd45cd" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "813aaffcd1c41744e44317fd5022dfab" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "72a16e5e828d053bf53e47139047881b" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "96bfd168a5a682486de38f7cd51efaea" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12075008 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 12091392 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 15761408 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "f0eba46fa401d8f5e38abad1942cbe34" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f45cc319947195cae13bc17da4f8ac44" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4d945a2a9b50c0e35d9aa28d588a0139" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cd7d905e075e2ba50377d3cd1cdd6d0a" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "396b9f6472ead8c85f8f93b3a5a8af8b" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5ab1e860a34ccd8c867e5009cb95d3fb" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "af5d1aeaecbd2a756d51bc4f09d1a5ef" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1796de442dd263949aaf6d400b52d6a8" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "56fa70711fc691d72440fb2a2f77ee5f" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "404440b54bc01d49ffa0621e7bd67083" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 28114944, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24428544 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 24444928 } ], "md5sum": "81a195f99d2450fb99232cb6e7828c8a" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cea788b14b7ce5c88046d3cc5ad4d012" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "2a473909f90669c791cadaa13903c102" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a0e55f4a031f1d60b9c5fec4595004d2" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "14a4a75f5bfcaa6b5cd6892ecace1212" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2e56f7251794e0dc82b60d7cfacc1257" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e1cd7013e76bdeb8ed3011ce1b3041c4" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bc4c0eee3fc29fd5ee8a6b207f13f231" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ffe5785b0533ce7fb29a92148e66d891" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "67ef2ad3980ca32f0462157c05471f0b" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "79ff27e1283a10ba8915a06872ce3f74" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9c067c03855675f5182d8462f326a493" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4ba94c992e81b57cdff96c873ea435bb" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a98fe8d912858017b2504767c064bef3" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "072eee2cd24ed93435bce3f00dd2f779" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4fa3bbc5ade797a62fa9b2889da12821" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "102688a5b6c101a25d50df4173df2f1b" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d7425da4fc2effda62a9c8bfd069d57f" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f93218d2a4c39ace6bbe61bd07234453" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "78faafe1b069ae5787b033a5baeff20a" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "46a369938c042a7f108cc6622826ff3c" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d0b2cccef8a9c3808c43fb64639c8c86" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "808aa3c77fc2ae077edb090d71f17cee" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5257bbfae5c1386cfa14e6ea913396af" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7effd45c34c87f7685d724f0371df1bd" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d603e742788d45716ac7fdcfa701f1a5" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6d5fc6f5ee4fbc78760ecf8fa8f95156" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "452e3e78901033c36af068bd72161c73" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fda2ea40d992e8ea416991106d3aa75e" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "272bc20db7bf2d511d113c113522acac" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c418db81e17c2614aa84a221144e3efe" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d4def0e94d1b8b993cc9c8ee49167cf4" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5fff51154ee0169af2b330a5116722ee" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d29f07e17faaa6f34ca2f04f43c0e8c1" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c4dd06a06b53931b6cd2db6beb661bf9" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2773a5d0a3e06b1e934d4e30c2e9decf" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "999177a914390a6115520d7a5265ea81" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "173b433d7ada4a865dfa88bf934f0a9b" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "5f3822e71e0b59c79cb2ecf57ac25d44" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "812184b84f9cd394df4dcaf18801dced" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ac16d491b3abb1ebc7c266a6a35b13b1" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8cdc416ab61a4460862874114c37f122" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "36d25919811074e06c2c700bb9098a61" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "969da4e8ff8b1a6f2867f0454e280408" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9e08eca4991d1c52468ac1c3b1d048a3" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7ac6b85e704d54b9830ccccf8bf86c05" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1ced723e5c9e1ad129eed72313fbaf96" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "669ee24fc0c9db1d3d7d2e00d2672f56" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "406f6e161c2f25c8c945e6556ee2e750" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "a67669c0e939a5c9b354f430a5738ae8" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8942360ff9206388080948027ce7ccee" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "58326c74f6e6e2063a4546b040bfe4ac" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ed4e010a60b707fb1fd5a2a7c1c376b4" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8df8469ba41fd5a7743bb855e8ed15e3" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e7e70621a99622b1c4254a2853a4c8e4" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1b43467990cc07b70d63ca4c47af507f" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3db1b65d8cc3c53287baa03492efd82a" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b1d097ed9209a3626c7c24c111949d20" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "dd2c8b2897c40bc3017a06f2a27808a0" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "43c85e53688c6cc10e9172a5266d2ede" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "020e010a421ae02c9e6f1595429abe59" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b82a5f6249e419f73a27fb501a90e191" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "db137f3180cd9f374cbc0631b56d2409" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8b838ad5c8bde9c82001ff359457bb2e" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b50b836b97b0acfa185c8be73eed7099" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5c49febb98ce89b038874f447f7b494e" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6708145eeea2791bee042348f751e393" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e13a70803ed75c9968cc839e30938cf0" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d539ffc933bd84f89492bccf8cd367fb" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "d8965512b745995159c805881aa34ca7" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "afbe89cd56652f0fb62848feb5fd43dd" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4436579bdb2387bf5e53d065ff264715" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "209bb98aa5d87442479c4c6ce45b2853" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a0cfcd02b57023ae7d5194d1fc2c9261" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a6171cbf12b003253c98e9a983aaeeb3" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "91a0b170ef42a172a32bef01bb1cd2d4" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e873fa97a10661538979502492be0678" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "115b05db06178f381f1d0029498fab8e" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "dbf77141b4f6c16fc3a76876f789b95a" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "25205b1483f54f7877008584b713a3e1" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0ae582e581594924b36e7bb10ac31ab9" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "74da61671ddab6f95b646d0986f6dde3" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "803d06b1d3b8ae2a6f0c2ceb4a8f01a5" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "021a71332bc5e1fe6bb1926a33320b7d" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5157d2f6059b930fe5b038a75fdf8dc6" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2ca2ede5aa86d7e475a399eb924dfc39" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "70a407dbda19022d1e5fc8eca786f4e7" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "0074079a61018f2e4117228d9be1e9d8" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "548fd672996c0b73ce244052d5602e4d" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "de442ddc85470bc0230aef48e1b3c73f" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0d52872f8b676440a797b31662643d4e" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "471bd550b59903d215eae5faf0d6ff0a" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "458c3b9f99313574c5d98656e607398a" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "91a940af2a56dd393d1f2687a178a77e" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2dfc968d9156ae9652ae192198c6c5d4" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "70ba2cae63bd3499bf0544970a1daad6" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b8ce21eec393e0eeae51c499086b37c4" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9933e22878080dd0bf117cc29b71eae8" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "60e6c8c52ba8aab7f698ed1cfd7e900b" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "aa6cd69b9150126946f1b138bcc95db3" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d3dc35d789f4d5ece24ef24795959225" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e7054e3464028d9f8ed6ca62fd5b9b51" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cfa7f852d4dd4fd86f19c42930be0cc3" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3729ebadda448f244556d0f984fd16ac" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b4f402a487231ce836efce4587092fff" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f7bb820ac98732f295512e447b6e9fa5" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5da1b99e5722d46c3d19402f722bdac8" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "9c7109dba4e1f5ef43f34006b9e94f08" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "85c0277498b2a1008c68de0ec079844c" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c8fc118cf0d558ae721d4db2a9545096" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "482ad91304f1a91ffa6e5e14090a7e65" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "40ce1a292d7a5b5ff81b4b66040e81f1" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4c5997b5bf30adc5296ae76d734a2ba7" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6c09d134e641548721c84f80d4cfe4eb" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ec22bad37dcf6f0890a4a7a32c31a262" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "59a0034927dc8b9031f300163424cfaf" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8205d493987c3f0873d10f1132242292" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8049e7529c92d8666994145e3b6305ac" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "1587c6e9aa8b30bda119b93db7fcbcd5" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c24022a185886caf6d2e8c61a2ef21b4" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3b88c7853365f82fb54885e934890dbf" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ca2df59f41bafe1521a0759e355b1632" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3fceb23c3181dacdc0ed908b978ad207" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b29ff40317d59916c9fe4d0cab17fabd" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e11b29ab5fad257036d52361fdcd0249" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5fc81c9152cbafe52f7b18a82a6bf215" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bde6db62013f9d73af5acb901cdc7c3a" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "0681073cdcaaaae72e61392c161ef2e6" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b5e272dc99bb6662f1f6b4ed2f11be21" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e9c27ae1b90075bf2c2da834c977eb35" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6353d8f83fecd9cae898b1e33adfb6eb" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "dd409b9f971f418944baf7ed28bbcbc1" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c43d2019623d5868b26b09ec397bb2b0" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6847807deb91c26e5f8eb330db8bd5b6" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ef653e2c3a0b5a0635d0347f042b2276" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c6b78c0f71c5fef1d146fed8d8adb117" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 26804224, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 9715712 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 17055744 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 18366464 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19415040 }, { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 19431424 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23117824 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23134208 } ], "md5sum": "049db096ded1ef5f003698ca49d7d4c7" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ace500e1405e7b7f1a5225f9d04c9d87" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6948e5ced8123fddb4aa17293181ecbc" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "292e73cf6c666cc057ce3a995f596708" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "64d8017dd33227cb23660157c1f33455" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "952c148cefd46fe27aeee3682e8b4d07" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c28bc0f2d475705bc8f8135a0f121bc8" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9bce3bab93f85ac7be11c0f27a395df2" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5713a7e9a20c8305ad0575dac9fcf374" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e53e55265de81f55c0eaeead43374c4a" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "fab32236e3bea83ccbb9a7e6c9e0e317" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 29163520, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9732096 }, { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13402112 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20758528 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22069248 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 23117824 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24428544 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 25493504 } ], "md5sum": "62eb31ab9854337d82725916786586c4" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f58cb10d044bad405a8f654e5f5091d6" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "86389c7f9dd132eab818e91944455e35" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0845c10cf23d6c1b70f9f62c27342c4d" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "93f5a323c874af895094d2e62a343fd7" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e30b4d1a65f7842a47ffec88bc682386" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "56ff9d00b0751624ede12dbb0a6a63eb" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cc634f77126943b78121d0e430621672" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ae124066d8587547511a1997f3944333" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "20360ac0961780ed40f04e96390ed865" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "2792455bd6e9b2e48fafd6d491eee213" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 7356416 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 8404992 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 8421376 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 12091392 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19431424 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 19447808 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20758528 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 21807104 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25477120 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26787840 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27836416 }, { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "eea882538daebe479cf23fcf3027dbb1" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "90b96feb0845e733967bc84f65ea6c36" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "96439aae1f919c90bc67bb0ad0cc7e65" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "08f132034c90428ceab5d897a029589b" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f76215fdb03bcffc73387094b93b257f" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b9c878b7f52a9e78e7e8450089efeec9" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "31699b0d6fa08f6793f95b6ba6b1185a" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2d4b0a466528dca904936ec8cf495158" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "764a2493c1eb071eeee9d5c640511989" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 33112064, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7356416 }, { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 7372800 }, { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11042816 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18382848 }, { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 18399232 }, { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19709952 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 20774912 }, { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 24444928 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31784960 }, { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31801344 } ], "md5sum": "b9ee69646926a42b18739b7b01970d9a" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d7cb5d68fff08a80fe030d3160992f64" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "47905277b3a786b7722d0be4cd258a41" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "da077530ba8dd1f77d4ad084c62252e6" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d132ee7c6aa70324546076528d4488a1" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a80f0b02ca777e8b4b4614fb2712b6ef" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8bc8765b39caca38c41a82ad68082e20" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "817400db93408d1c798d6157bad8943d" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a27fdcb984112106b32b98aa184131e2" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ebc77d1fc6026642d708deadde299f20" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1bf5c92fcf166651822e52a4dcccf646" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 31522816, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 1048576 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 2359296 }, { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 2375680 }, { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 6045696 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13385728 }, { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 13402112 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14450688 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 14467072 }, { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 18137088 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25477120 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 25493504 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 26804224 }, { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 27852800 } ], "md5sum": "146d8c0de8a20c73c40be82e428dd452" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1f162cb9c67b486759b52f2062b3a1fc" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6aedb661e4ef76f690f4f720143f4c6b" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "df9d79cebd29c3077588168932add72f" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "988e2e3c7a39f57f50bedfe1a30d4561" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d8c21e423b8a6190b660a056337e1e4b" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "75356e255693890fb480878b9ad61814" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 3584, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cf85607eb8f4283614c49ff884e81d71" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 1024, 57344 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "975ed2c25cb8b2f480ee2f9cc8ecc727" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 26820608, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7340032 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8650752 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9699328 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9715712 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9732096 }, { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9748480 }, { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13418496 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20758528 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 20774912 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22085632 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23134208 }, { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 224, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23150592 } ], "md5sum": "c5a134cee3dc07ab03bea2e2bb9d7dde" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3619cbfaed8fd69c7e9387b4721f36aa" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "72e3ea1ebc44bebdbc3b12e8a6dd88b3" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 1024, 10240 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b50945f70e26100604bf42d3917b23f1" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 1024, 8192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "04d4c3bfee4885d799f7af0761449510" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 12075008, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 64, 57344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 7340032 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 7356416 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8667136 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 64, 10240 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 9715712 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 64, 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11026432 } ], "md5sum": "4d5d2f82a9e63e34a558618f2fe67ff7" } ] }