{ "metadata": { "ParamSize": 399, "ParamBytes": 1736187904.0, "BitsPerParam": 4.0886310227871485 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "7ec678756f43326f92cdec5b2c49d489" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d26eeecfcb7efe5ebd789e3fd750fb6a" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 31020032, "records": [ { "name": "model.layers.28.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 0 }, { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 4096 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11276288 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12685312 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15503360 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15507456 }, { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 15511552 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 26783744 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 28192768 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31010816 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 31014912 } ], "md5sum": "3a3285e17a72372e45f89552f81bf833" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "f8a70cf1b794bb3f12ff1aacd8bfebd4" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 26133504, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 5312512 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 16584704 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 17993728 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20811776 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 20815872 }, { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 20820992 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 23442432 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23770112 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25867264 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 26129408 } ], "md5sum": "259a5e50b8e901e210fa6340ec1136c1" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ab9b30715e4e4f31ad974cdf788e4280" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ed5d97df2964eaaca8f3e2f8102c9914" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "357ed1fbcf2a706cc3c47e248681167d" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "f8b991f2c8b23dc595caf6c34526f5b8" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "4a508acc01a03b82e1608de33a53b786" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e29bb691e609e29c1628557db7e14722" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b5c7f59efc3455a85949210651b88e6f" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "5199dfe5bb161e2ed749377c091c13e7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 155582464, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155582464, "byteOffset": 0 } ], "md5sum": "223ec00669a36634b88107ab632c8573" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 27591680, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 19447808, "byteOffset": 8139776 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 27587584 } ], "md5sum": "5a527530a4043399e350ec2f465329fc" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bcd79b947e6994271f3e4ce912b7e74f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "14c06a8f518c9d8ab3fce158883efe50" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "6ea859159e367387913845ce93654b9a" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bc610ffb813e545165086fefcd1d0be4" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "3cf366ca2faa2b285e9adcf52a88a8c0" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "20bf3d29435054657d46049d6b8cff3a" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "6723aa23057a242192683409da81bae7" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "92655d3887586040fac3a59768c3d1bd" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0ba396453a8106979127af8d467cc9d9" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "5ee7484f4bfbde9837c8fbf5edb0dec6" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "6c9803930168c1a5f0e699b4df208119" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "dceff999545ebeb96998866318f8f480" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "75a07209783bdee74e02a7beeb170b3a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b3f8535e86ed4dd9150c3b1de2fb8fc3" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "7f765afc756d3eac5440963d3f2dd84b" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "efbfb2bb48969445ce569a54fc8a0451" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "4586456266b52cee89aff1716b2b104b" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "cda4ad31477387b8ecbf1d829c83a7b2" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "124c27415df654665c12eaac7031b5b2" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "db98323f85db7b423bdc946c86b672f4" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ed0505a8d7d1352bc578e4a1313fb31c" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "67d40b84889ccd5bea1b92c54512fe6b" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "bdc0ca0d5afbbdc7102526dfddb51646" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "73dceeeedefe9e6b7fa3081d3a05e38f" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "30fb14be76f748ad49fb76e6d0e34c0f" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "54fa780ba0330f88904e23201f62ca69" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "242a11e351de821435895c7b64b7018f" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "fc1a201a6268c3333c24ab3c32cfa8a5" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0662cd724de1c9840e3a4a33ccc17510" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "07fb1e148edcfdac9856df99f6a7f297" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b55a912f88880a2e12bf7b80533d5711" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c98adac32b2234fe4354f0f8a14f771d" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "0970fe0c84daa05261fd4a2200fc002d" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0029b1c57a3df691434fd6c5b780c104" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 31910912, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 28956672 }, { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28961792 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31583232 } ], "md5sum": "44f46869654502fdf222a5167dd95572" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "cf8e72db06bb11ea146d473e31c06837" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 23184384, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 2363392 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 13635584 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 15044608 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 17862656 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 17866752 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 17871872 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 20493312 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20820992 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22918144 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23180288 } ], "md5sum": "a8415cdd7560d7d399e65d8a0955e1bd" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ef0f0fd950d4a25c2da84a005c426466" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "eec9d9a0dcabe09b6b3325fdc71a4542" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "df66290024ca8f6822ef636983e7b494" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0e23241256642ece81d06157307580a6" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 28960768, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28956672 } ], "md5sum": "eec50d2b31a726abc135a0c4000adc25" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c16c42aa8270c0e4de04ac5405962a99" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "9cc9d897ebe2db129affaed0e91f8685" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 33502208, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 12681216 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 15499264 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 15503360 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 15508480 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 18129920 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18457600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 20554752 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20816896 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20820992 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 32093184 } ], "md5sum": "b76ce5d7c307eed16b123845bfe1aaf7" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 22016, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b60a0b0c38feeeea40385f567567c14b" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 28956672, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2818048 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 2822144 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 2827264 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 5448704 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5776384 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7873536 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8135680 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 8139776 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 19411968 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 22016, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20820992 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23639040 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 23643136 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23648256 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 26269696 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26597376 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28694528 } ], "md5sum": "fa56bb2b578bd65dd5f8fa7e9b7f83e9" } ] }