{ "metadata": { "ParamSize": 437, "ParamBytes": 4607731712.0, "BitsPerParam": 4.500432754306446 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 311164928, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 311164928, "byteOffset": 0 } ], "md5sum": "cb33c73700d51245b4dcff8dd9819014" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 38895616, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 38895616, "byteOffset": 0 } ], "md5sum": "68441c40d2b58d81a8ef1a9f50ab3062" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "18e4e5a7e9c4162a672a5fa1a0e29c14" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a6bbdeb88daa10a12e1338bfc98b6040" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.0.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.0.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "0af1d5c55809cffb4a8a91382318434b" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f94dde772f560d1bf9a0b29e510dbd5c" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6640b4f8dd36a46434185a9b952c5205" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.1.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.1.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "7707661570b6b9c61f7deb3e82b138aa" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "822cf938bbd01bd90da1cba5723de76a" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "619aa87a725ed742c8806837f9d00a99" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.2.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.2.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "1ddcdd77f1a457c30ffbfe02d9a236b4" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6292be532a8954969627c79b8f8601ce" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "02e86652cfd5d5a50568047c53244a0c" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.3.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.3.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "e38a135b718b494774e7cb5c56765555" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ea722d088a8b4812f1a2c7ffd7cd537b" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "26800234d819903fcc1c0a044f43b4ef" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.4.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.4.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "5175043fe4b14bdb747897f0a0c1ddaa" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "bf42c8bc1536da4b05a93b820a60744c" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a465510cc9a75cdd584ec4a971cf28d9" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.5.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.5.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "dd9d60e849a94feb872a8f6466526632" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "55b73eea31604611a058ff2805c745e8" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5ffd72e864eb385f7c30936ebcef5e45" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.6.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.6.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "096a431f916e9f9d764087a19a8cf550" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "da713c212c45c24ea4304c5e0bf6a9fd" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "bb062dca51090e1c008cf9adb46c91a6" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.7.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.7.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "a6a51d0d3eb453e5e957089a5bb0871c" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "dc21b61e065804d4367a866b7fc3c10b" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6672bb3e58a8e5c233eb48909d9e787c" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.8.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.8.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "d0d81ef9ecccea18e3de6abf158f41fa" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "15c11f1bfaa9d8500b3df8b621a2cec3" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "749afce11f57e096f5767be821fd27e3" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.9.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.9.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "a35fa12380c5a831c11dc553c9bdc074" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6ab4de9dc92151922157eb9472de3a54" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "03212ad4249a2d81e770d9676ad66024" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.10.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.10.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "6f2b3f06545f516fd9b8610e5011e947" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fce7203d3f7eeef36f431e6fcf8d32d8" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "234d64476d75e2a4f8bd80935bbf5979" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.11.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.11.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "1f808826601511b2d1ecfb7008095703" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "b4eb20feacea3546a3a517ba572c6778" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "eaa7e9778f37128197fdcf3efbf9f3f3" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.12.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.12.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "53691e1a9cab527572ab92e61f3738e3" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "dcc17f2bf4806874c90ea8af14ab622e" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8533fbbe58d7fc05bfb2b4f5a23986b4" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.13.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.13.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "3777da0f3e12863bb3212db9cc082cf0" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fee5b2154c918b9945a733a33e7a1505" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "25809531a0835e8d1a538b447347e632" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.14.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.14.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "50cab3815dd67417d005b05f1feb90ee" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fe1efd8ab73ad96b72aa8e0a3ab762b4" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8a5b5fd65164d55fec2420d93bc9cdf2" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.15.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.15.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "27de2843975a88d5fee45826693d537e" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "e6519f5f7dfaf9d7cb99bb6ce00e5b3a" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8d0c84b042c6315b52cdca633fb70708" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.16.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.16.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "29c022e41811df096994402ccb49ebe2" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6dc4085a2b6c969d0139fa5f1d9a4851" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "bf0dcef077224f92acba8d9afe01c9c1" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.17.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.17.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "6088fa5fae94838e54793347256e62a3" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3c71beb0d3f8430f05625609a86ee4d9" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c51e9fc720500bb727c8a21ae40fdc4a" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.18.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.18.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "ee48b3a20c4ed76874d4082af0664cc8" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "93b862e732de91f87b7042970af89f8b" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e201210c629457d64a655695eaf34b9e" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.19.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.19.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "7fe07308aa0b0d8f7b4d321908088ba4" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "abfe89b50096334e37c3bf3e1eae1c54" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "98726ee240ce7bef359e8df9ec3e88db" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.20.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.20.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "83854547d80df9237495370b2d64ab03" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "33d556147325b52ae9c7557f46b27616" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9df1ab9af4b06ed8fc3f5547efe2d497" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.21.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.21.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "bcf6f218c380a74dd41cfb60270f4418" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "4b83a72ad6994bb3586d244b39a8be85" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1c40b111c56a2d5d98f846abb0101d01" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.22.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.22.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "f3a9f16755082a6dbbf411e549ea8e97" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "49202480bfeed28a6aafceac9ee7e9dd" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "697584b90fc131b4cbeaa088a21aec39" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.23.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.23.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "d1301dbe48d766e5e7eafe679ffcd444" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c8e68e078c28552227427c5d30d8fa6c" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ba1f1868765a810418a9d82d177d7e3b" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.24.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.24.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "646902ba43d5a26abc47cc4face15fda" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f4cb1c246889efda95aee2f681b821cf" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e1fd25d9ed693c06eb4a75579ba34cc7" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.25.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.25.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "e9118721141d82b9651bb4731c7f6758" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "9f367c886492d9172c026f4f52692099" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c19e2ee4d87be763fde58d829c91d3e1" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.26.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.26.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "c2c271e4bc87233d1e81ff50f3e7dea0" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "abe0e7f325267147dea3f0066651c0fd" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b9c0093858bab5a31fd310780254f2c6" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.27.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.27.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "bf563657462a81a731cdf23f5b625464" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c828b9c32fbd242d0f733c1532004677" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8ce57c467a2e2078858462e33de69449" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.28.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.28.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "4755b16a6b59b6794e8772652ee18887" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3e33b38651c6ec239d926ee6007606a6" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4739522b1cb0fd79684007943451118b" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.29.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.29.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "9f1096d8ea9a8e042769a9ca97415385" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "f3986d78f256eb89700a296f59677baf" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7fa7b2a10afa34d7d20ab689f7c45443" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.30.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.30.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "1c6a91856211f964948fef13fa73c78c" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "b2cfcfd07dac732386b786dacd89e2d2" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "86412f43f8295ffce53ad7c0420c8778" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.31.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.31.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "996c5266b3b308b5d9d53cfa15df0954" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "d2c1043d750ababcd6b7b4ba6fa8af4a" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4408be448ea5fc55a5a9d88417e3f669" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.32.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.32.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "32a168e0018e2b59829cb6f4d6f68bee" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c6d785b15bb5aab7dbc6bf0c00a65597" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "43659173217775cb5a2b844aafc3f65d" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.33.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.33.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "2d1e9754b308c7b4f796f0f587ec9a10" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "80882600f22eb61a151c1c5f2ae44b21" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0fcf04f2bf504682d989fd61681a513d" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 33047040, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.34.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.34.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 } ], "md5sum": "105a4438e5af7429349855b47c0222dc" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 24576, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "688513890d23e17cdd68546d91383c76" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 4096, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ae4bbc76350afcd28011fa55d30ed0b6" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 311164928, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 311164928, "byteOffset": 0 } ], "md5sum": "28ae7984b32ad1b45ef66d6dd81d015d" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 38895616, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 38895616, "byteOffset": 0 } ], "md5sum": "48618490c345d1a40d7a39b4a1199994" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 33055232, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.35.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23592960 }, { "name": "model.layers.35.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 23593216 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 24576, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23593472 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 4096, 384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29884928 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33030656 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33038848 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 33047040 } ], "md5sum": "4bd896eee7d9b9bbae70613d9ae41e8f" } ] }