{ "metadata": { "ParamSize": 183, "ParamBytes": 1409830912.0, "BitsPerParam": 4.500347711112945 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262144000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 256000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262144000, "byteOffset": 0 } ], "md5sum": "0b8e94b0315cfa59077a47301e097522" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "d0beb0c86362bdaa10f118408e315847" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32772096, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 256000, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32768000 } ], "md5sum": "f379b208c95b8217c994896c7b6f2498" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "348946c3fd386299bb0d2fdd46aa9046" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1c4f59386a1bcdde955ab7b914c3db86" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 30482432, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 2097152 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 6291456 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 6295552 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 8916992 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9244672 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 11341824 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11603968 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28385280 } ], "md5sum": "196be38ee65373475c84a511d40ac85a" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "235a4d21571ad0cd05ea5fa2df18864a" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "394ab6a7ec5b2665bb6e4ed71a3dd372" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "247cb17fdf8aafb51d4ad7296cf2a45f" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "f9181563cd46d7af10db91ab2ed0ada9" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2fe9ed5da777935a4d3acb667971e52f" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "fa8bbba1912270648f80f205ebcc7656" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "addf19589acccadd204743c5add309bf" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "e1ca768dc62074c18d4e0e2c3a3f0438" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ac4af4d39d2dfa3d8faf9f766ceda009" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "310d2ac6704378464aceb1904b37a23f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a5e366406f0b2cc2b1df26391964bad7" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "70723855325458750f43bfec445a22d2" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ccffde269e3749b05154bf0ee483883c" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4706d46c3287315bb5d804c8378fbc0a" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 32841728, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28647424 } ], "md5sum": "857cb613d391e2e882727c59db05d4f7" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b1fb11c49960b2fad5fb12df3797e5ea" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "6acb46df7451c7a109e969108ddabaab" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "357a23b7f52165f3a02a20786b96034a" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "7cb9ce40a463c3374e378d906ff6ecc8" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6ac6057b3b8b9a0575709be0d1f134f8" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "3ae8ca8e0620e5e33376bb379ebddb2d" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "589321d746ecb89b0decc1cf0946dfed" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "cd32203a2eebb05822960f7e8d5ba953" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "65fa9808888658ab1e7f9f2b8eb9e173" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "8cd575533c288ef4ac18b3245aede3a6" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "93459a2408527d8f9583892ea4116ae9" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "3074cb1d09b2f99681653de0c979ef12" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e50311a4a6e82a0148edde20a9962c60" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "f0a9a64b4b58907606fc77cd5ba1c70f" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 256, 32768 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "148052a76b6905f9918379ae0e78f6db" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 64, 32768 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "bd3c8abd3e48b0ef958569fd9bc197df" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 24195072, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 256, 2560 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 64, 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 512, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24186880 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24190976 } ], "md5sum": "b2f4f324b086d629dd4b3a5e8800470c" } ] }