{ "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": "76834a66b447ed959a5dba4862338312" }, { "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": "5706629174af79cfeb92439752fdc945" }, { "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": "9e422ea69524c5742c9dd90ee1489033" }, { "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": "ef73d55a46171c99c30a4b590a9ca5ee" }, { "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": "7c1509918451a49df944329e01e3549c" }, { "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": "70c3a4032464feb4037d1cb33950cfea" }, { "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": "3e80e2b4cd5ea1dde1b463d8682285b4" }, { "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": "5b9bc15793441be20aa77d2d4a350f28" }, { "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": "d181ebf2d388531c80ef81a78648a1a2" }, { "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": "c95904949c26b47f9837cef8668ba59f" }, { "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": "42fdfdef261768182fa76f673d3dd20d" }, { "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": "129b3a3b19f6ab65fda0eca5138ed013" }, { "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": "2cc21823cc7b9346681fffebb1f75ed0" }, { "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": "2979af8d22bf6c5a03eeff7925278147" }, { "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": "114e300ea2680084ae0f408a5a04b050" }, { "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": "372da8dbb10e570f95d8a1b08993f6e6" }, { "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": "fedcf8c7d3a246baad9dbfac127436ac" }, { "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": "29d50626233e1af9d7c51a32a8cc2106" }, { "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": "4cdbd9a339239468f0d4d6570b66bdd3" }, { "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": "9e4ecdaa6c3be7ca76f538c3f6324e9e" }, { "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": "d84dcee5f133dba81276f791fdf14b1e" }, { "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": "1e0d8ceaa3587d86245358080020e1bc" }, { "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": "8d158b4a153d626ed4a86ec561a58ee0" }, { "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": "d4da995026501bf0a2378f038c590dc3" }, { "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": "e055e4cf3b03a9789a371e439c6943e2" }, { "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": "2c4d526eef59fc7ccdbe1f0a140c20f5" }, { "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": "d3026966f6bc4067e43fbd15eedd268b" }, { "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": "53e520cb7fa7abe8ee3bc5baef193f28" }, { "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": "eb9b82a97a37adf5d7a4a3c30dd90a3e" }, { "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": "0964c066b2dba3c9bd0c13fc81aa847d" }, { "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": "48bf6868723196a709f18404bf8e49ff" }, { "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": "5900b1181607a4004ef494a36b319f56" }, { "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": "6e7cd5014d8ee5a1ca5eb73a9b58666c" }, { "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": "a83ac151c42f554cea6c6bb94ba0f1c1" }, { "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": "451f725d76b25f93509e230024934709" }, { "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": "d2405822bb1ce59620572f678f0ed8fc" }, { "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": "bdd5652139689bc22a90a07b6387219f" } ] }