{ "metadata": { "ParamSize": 243, "ParamBytes": 1069948928.0, "BitsPerParam": 5.001583230915965 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 49152, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "04626f4f879db0d2dbcb01fe8f46807c" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 32509952, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 49152, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 6291456 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 6295552 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 14684160 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15732736 } ], "md5sum": "f45309f2cb98e3eb9a24c7b5eeaf8bf0" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "a367b9d9aaf912c90fd264e01930f7a4" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 32522240, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 2101248 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 8392704 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9179136 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 11276288 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 11538432 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11542528 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 19931136 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23076864 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23080960 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 29372416 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30158848 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 32256000 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32518144 } ], "md5sum": "fea7f451dc5417eebc1e9ba1a5f5e79a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "7c88c632f9d5bb03ca67feedf2e0fec6" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "69fa58d8e2b24cfbb3e371fe687eef07" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "db8c249aa44c5879767eea1ffd54afeb" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "9021c94e98ea3f980efcf95dfc6a0325" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "e93ee9470e435fae28b37ec7dce7b91e" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "b72a0af656f2aa812ce5c7a86ffd5d10" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "d3e8d0bdb8c5cf2b25f9af0489195bf8" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "ccbf7edefaef1f2b6e8b7741b75c0ac9" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "845fe813cda20614ad2cc5b0c4c788d5" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "aa1bcabaa351b9986322ffe48c739126" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "733b4fd35cde116450441f1bdd3718e2" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "8f5d019397ca0e05d99ed7c6538886f3" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "a4ec7629543d4c5a20bb159695496cf7" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "7a6e18806741ffeecb3c43c638fb6281" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "83bbe497d73fff117b07a925e65a47c2" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "75e105bc33f07ab7e293f84137d1245d" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "ef03771a2ef7f26ab57ae5a54a92aca7" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "b85353f1196cbf5c6b69d60d026569d5" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "2bfd8c4ea03c4286c48f8ba55743c2e2" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "02ba8bbfa29c8a36e954c7c160ada6f3" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "c9c44c764f557aec72fdd3721d58d1db" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "2ef0ef32d0c21603210638d0d111b2be" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "ddbd1399f677bca4ef66f50966efae29" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "9e68d308303faaeac08e9fb04a547c52" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "964273e8fece3366fe001e4ea1aa9d65" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "849251227ff2933f04ecf3e72efc0141" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "c04d8a58f5230ab419a262876b552c6d" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "0a81f170f10026d03a1ae981723dc894" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "f983d87d81884fee797738c8121fa74e" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "69ae9a0ff4f55e530d3a9cf2d98a2965" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "53f6ed6816cf19fc4a2dce7bb49d6198" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "51f2f5c3279b1227e3246b9cbdb92dc1" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "7a8a0babf4e390c9f4e4f764ed489ed7" } ] }