{ "metadata": { "ParamSize": 325, "ParamBytes": 3734421760.0, "BitsPerParam": 3.0339086581997106 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65540096, "records": [ { "name": "lm_head.q_weight", "shape": [ 32002, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65540096, "byteOffset": 0 } ], "md5sum": "ea8fd657d346b6ab7db42c712fdb3ee4" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2e50bb1e2a4d730b4b08cd3a33741876" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33267840, "records": [ { "name": "lm_head.q_scale", "shape": [ 32002, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048128, "byteOffset": 0 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2048128 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 2056320 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3891328 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3899520 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 3907712 } ], "md5sum": "38579cee3463dca347c8731857e60a2d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "6d0644b29fc04f32233ba1f1639581d3" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "5715c77ce324e78651ff7777b8afb89f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2b6b0e7166e0684c259e11c36a3f7669" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 27156480, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 917504 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2752512 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 2760704 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 15343616 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 15736832 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24125440 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 24395776 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 25313280 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27148288 } ], "md5sum": "4e41149cf1822a582f57cd6aee257e59" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "47e9764e791481c1bba750ed1c476dd1" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "237bfd343ef0beee21c97eaefdf08e54" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "d18d0523fa84287c0de1f3140880a72c" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "da8bcb09073e47bc9ad0ce88d9e7d271" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "8b7e3cd190ab71a8eda2bb72e6ac973b" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "f763f954a9f08b06f007bd139bc75903" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "74c4c6487a2767d1f60f65cae853157a" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a5c997d62f17157a83c3f263940168a5" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "7e77c2af904260c8576724cad950091f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "437bcf521470a9d16432684020ec107b" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "51b3e7f448b44675403e778df700b064" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "e38987e956c79101731cf0eb5a942ec3" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f1cd537cf16d47485bc618672dc60a9b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "0dad038bd27bafb4e569c5737b56337e" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "a0e5e3b1018322cd607387503dfa9a44" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "de9217e33cdedba6539c15b7345ffa75" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9115df7946aa80efae96a89f95f71e45" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "7ae3ef5d0b352e94cf323187066f0d98" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "232bd602c53df426b70aa4cf3bf1faab" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "0331042495a657e8e99924a399e24d18" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "6033889150ac0fabdee0da3d67839c88" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "03801c056cadac18f49eeb0e99d5d16a" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "26de7db5572241fda3800a85cdb93a5f" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "5ed04e00c8ee85f544d00e77153b7f3c" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 65540096, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32002, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65540096, "byteOffset": 0 } ], "md5sum": "88ffc3d1063569e19c4af6a9cbd26604" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2dcb342f59f630acb025c896002eb7a2" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "692f829ba04ab8078daf660490cc3bf6" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 26452096, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32002, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048128, "byteOffset": 21635072 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23683200 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 23691392 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 24608896 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26443904 } ], "md5sum": "a0d8b476efb02a4cf4cc4281526ad4b1" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9ec0ff568358be9ec0d5ff5c533f849f" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "818d38bf05f4a3f363480fe03ea6c7f9" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "567dedd49119aa3218cb9635359502f5" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "293b11d9c3401937980d7d4333f42d03" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 23461888, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 21626880 } ], "md5sum": "714579d026da4120827d22908425c7ff" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b5286dfcc51eeafd7adb1818b3188148" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "670ec88897dff984be37ba358931f999" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "b7aba5ab515e5a7a991140d48da96800" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "927b488188251134515f67a02704dc2d" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "568e1e0a25d12f7ea23a9ab85c291393" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "2789f00a9d5b644982d8757756ed0419" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9d4832bcabe8882bceaea98429acb714" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a84cca82e117416b60bbe760c73b9921" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "66c3592495189c90913c73f68ff1fbf5" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0a3f346ea7688e601777bc5c56d94fae" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c04014a701319aa1ca45896ba09f8f28" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "3e8c6efa53db282769122c6f1644d51c" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e63ee1c2e88e8a2f53eac52fe24890f9" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "62dbe899d561a4239eb5f707f12d798d" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "fce707347d3a82ec5809b841e32f2efe" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3abf21b1aeffe473f118ea7ef22252f6" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "55a18a331617a8c6b4fbc5c30dad04fe" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "4b072d4b08a13b3c66f9dd3da0f0a9c2" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "62dc8f32af23b713e41ae6f9d1fa8d3a" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "bd318d758a9c120d13a85ef1b1cd2051" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "e0f3d40875730b215c225b749a18d40a" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "aeaeddcc76e67156897975e7ea55fac5" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f3251868058da40837133d069692b086" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "e0dc65e3077a458e9b601aa784ccf9f4" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "54d9b983874d5d6539ff1fd75b85de1c" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cc0d5d15b48cd2797019f65045bdb4c3" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "576505b378bcab5df0172d323466feab" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25329664, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22552576 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22560768 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 22568960 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 23486464 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25321472 } ], "md5sum": "6f131cb12d429359e4f85264c82d3880" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "11b88f36e64ebfdbffdaaf58efb31733" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ceaf337f779978b8303c5b356982d398" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "c462ec85996f911f34a6784287b57064" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "27f515679163a7e80932f11b61f33f88" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "85e9bd66df927d660e2e94f1f9d56068" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "7ee5f2dbc6279b6fd52b79e2f8f9acc0" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f67f0a98254084e67c54fa0039fdd750" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "b562a904ceb3dcad1715635d4fbfe6d6" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "e6bd7980bfc2ead00fb888af079bd7fb" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "69f56c4eb0f3faac1a36ec25ccd66f45" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "622a3f54334a8a2e58955cad10a27914" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "3958daeabcfec63b3d11105e5dd4aa55" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b8b31b9aa26ee503394217449d12af6e" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "164cd29876509e219806f61437f438db" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "f89e470f8df22f486c4c5f61733f9164" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "7b2e711952008752971fb5e49009ee9e" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5d838d101c946fd53f11abae136c46e7" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "e5b53594e9c929ee05f550c64d385cfe" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "728d6d63ac981adddec91340a005f0bf" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "2e07c9b65ed5d19236768f8aa6cc61de" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "d027d5706781ad4c00d3b45e172792a8" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ebe590fae86109d82e3df95cd9934f92" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5f8ffea5b7de6cb472ba45b440a9673a" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "515d3544bf8044ab87ebf19f50586257" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "24f2787c4b5fb8dae1bc68c961f8e01e" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d32802ff7fe1685199661c2ab389ca93" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 24395776, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21626880 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21635072 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1835008, "byteOffset": 22552576 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24387584 } ], "md5sum": "098d09e8c24fbe439df401d9f08a0af1" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a1348aebcd4ec68647a2374a26609feb" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 112 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 917504, "byteOffset": 21626880 } ], "md5sum": "03b1d4ee73da6e33a370fc8ed0ffcc8e" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 21626880, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 12582912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12976128 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 32 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21364736 } ], "md5sum": "6147a77ff535d4c3260f6b6c87bc1778" } ] }