{ "metadata": { "ParamSize": 325, "ParamBytes": 3790741504.0, "BitsPerParam": 4.500454373872803 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "1df7f8c93d8d24023976aea5c025b3f9" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 30744576, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8192000 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 8200192 } ], "md5sum": "a5183287f5d43a6edca2a731a60747bf" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "29fa93cfaca2b79caa13326d48aeed85" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 28196864, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2818048 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2826240 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 2834432 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 25378816 } ], "md5sum": "51ee120ebfb9701b60783ef5158be0eb" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 30810112, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 5644288 } ], "md5sum": "47e8aeadce44d984620c9c4e02b31fa2" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0d1da7480d8278eb47910c99a4ade83a" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "2ee5e6c3a2c0ab517e3c59b4ef9f4df3" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "84110deb23cc5149e9160c7cb43efb19" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "55eb19e052af021f802aa0908323404d" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "cd8b6dfac5ea99ddd62d2e97848b2995" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "11bfa24639f221bb3450e20adda1c0e7" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "313bbdbbc1c3383dd76cd1cda89f2a6b" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "531933d7cd923a6a0c14ebc94a4f9aa9" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "90a5f0b4f7a96c8220bd05c5c4941bf1" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "95e209a54297513af85e59526923a761" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "7c093c65c290835b8daa8a30597cbf7f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "0336c7aeac149d783ac0a71ada69ac8a" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "cb2d7e3128834af312f1d6e11a7003f3" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "8d541eef57006e9fd4f1aa229183af0d" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "1282963b2e5487195322c0b4d94aada4" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "735cca7701046da28bbf98ac1cd82b1b" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1213ff3a8432d2423a33b72d1a94cd94" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "d9ddf986ecd5a2c1502906f85eef929c" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "bf605475c13ccfc154faa31b260c1c89" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "dbc8df97d0e966305e475c8205d809cc" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "0715b62954b2043ed680a2c34e2d29b9" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0d8a287d1085069a7cf4320846611ed7" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "83a6fdb7311f7f0816e6a9c541beadd5" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ecf84835561549045821803dbfbbd304" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "f308a7249f5c0ea64fd31e674f42ab11" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "9993123658723e0b78e8412298304960" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 31801344, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 1056768 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9248768 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9256960 } ], "md5sum": "4a16eb47401e73ff536febb8c625f496" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "171e938eb1abefb63757a193f87cd5e0" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6577bfe67dd9a7842dde6d8e96628308" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bd276d37327e515c6bdfbe495096b829" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "58382f2ccf032a12cd709f6e497c633d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8a449ed8cf99a68443740fabbd64c5b3" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "0699bf6bbce1e3a145d98c4ae4b6837d" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "46262d6ba7590fd0a9325ac94c149b0c" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "cb90ece32e4afd86865e384614acb221" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ae912939c80779eddf54819c218cf58a" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f224de8071a9f21c4b698241049e468f" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c99a834260b5c4f22bd8c704877815c5" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 29827072, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 21045248 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 26681344 } ], "md5sum": "23976ed1f70c2fb1537fe27aefbfb588" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "2ceb776373fefb7fa5fef84a341b0ff9" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "4459d2dda52dcbf1cddea2487f8c254c" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6c82c12cad18478168a68524b00c8dba" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "8b090a07365e24546777282c14aaa95f" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ea6bceb60176d39f4bebffbd9c50f3dc" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8bf9c61db1eb81c321b4cbbb2301446f" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "838c291d25cf24d3dcc40e5b066b8bae" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "bf7b68cc7ed73965cb88b33daa29430a" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "168c2825ceedaf82c3975ff5c2ca56ca" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a7459fb283c133f97173685340e69e50" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c713dc7874739a5dfcaff2d1de9a781a" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "18edfe35b81bb0b3c6b57995d2995c26" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "74896b80f699aaf992c152a3589b7cc9" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "74439688e0d8982eeb693f24641eebc6" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "140142a5fb9e6003910dd56d85aca4a3" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "0e137e87a72b4ce5fc9e1c8025d3bea4" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e098575ad78439fe5bfe34291a8db678" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "884debd8f1676541a21d46ce1d6135fc" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "5110cc8196cb91f801cec1334fb58482" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c4c801d03b96e344b244bcd5526879fa" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "5288b7b836ebc0588e1f206fb604d7f1" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "40a8a9b05692bd4e7b0a38821914561e" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a07131314761d106358697d81d9c9209" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "abbe854a6980880632a814622b2b537e" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d5fa37eda40bb50cceca20c4771342ed" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ba7ae28535105bc09e06a9c3f782c709" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e887a6608fb87e572c8b9e1c2c760155" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "abc6c6a745d4eb346dc5ff55d2fb5e5b" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "f2911ba98e0f2061685ba1a11b18f808" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "8dbf168fcecffe06d4826fa9ca990377" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 28196864, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2818048 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2826240 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 2834432 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 25378816 } ], "md5sum": "f09d916208bd62d9577413bc34b0899d" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 30810112, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 5644288 } ], "md5sum": "2ea5ff6263635ab26b361d22cb27b0ce" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d10752e486dc93d68d25436075fc70a3" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "6f4ad0c178f4c12fb7478c2c42405b50" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "18e23ee71e43a821b6d381f13d3935e5" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "464073a0b64f4fc08af6787c191cf1b0" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "d1227d6ab84ef636f349882b11cdb8af" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "815cb62793d3a1da437d29405082b188" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "bd4d79a5275d3112bf6a3ba6d3d60ffe" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "a69c7526c2ba92d782c59a2c4b5e4b08" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "6b7ca6992c3d2ff30b468dfa3915ef8d" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ba1ad46a9d1c72e56918fd446786bd01" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "3e1c2ce34555ff9993c84e9e93f5ff11" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "9ed5b5c12b678c42cdedb91a76cdc281" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "43b2b422386d72ad3f7c2e0f883cc4c6" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "d6165039cec23701a3f45c36c9143637" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ccccf0d41a9bc0d5b2794031f39bc0d9" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "3cf4d310b83b1a71d0bdc90da3834b4b" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8868c6895f08ea3fcc6fb7f9ffa4139c" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "1dca547caa7891418aedc0002af0e136" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "2c6e64dad57f69e40b4279f61815ab87" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "135369dcbc10a3a2734493a95fcb55c9" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "0748f082cf543d720ed83e2da15c4da5" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "882f6a42245a91602d2bd9be10b09e02" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "7700694a71fb465fac5c75dedf98ed1d" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d40583ad3ad87714cf998275daa2c14b" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "ac1463b311fe9eb0aac6a820628fbc1a" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a0dc845b0a004f065aedf41a1fe2da78" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3abc51336af5051138f5dff2ff94c84d" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "889676c7573a5360a6fc6deb1ff37643" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d4fe63bb273b8c875a648fd332dcb182" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "fe6a854c8f891fa40345e20b796d7b0f" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "939e66a3352e470297efedda6647c75d" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 32587776, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12582912 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12591104 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 15409152 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 21053440 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 24199168 } ], "md5sum": "c3c6799d6bd960cf640b92b1dc2b76bf" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "99640f87de1bdf01241b82714d50a76d" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0bfda1d6a412964afce66d720d4db1fa" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 32063488, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 1048576 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 1056768 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 23601152 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26419200 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32055296 } ], "md5sum": "d317075a1213fbedcc72a53bdd28dc0a" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "c163099177f5182f51f13ed65ae7cdea" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5b290fc529afdc531340212cca8481ef" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 30801920, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 18219008 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21364736 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29753344 } ], "md5sum": "787e2c9036bbe2bea3d98eba9230155c" } ] }