{ "metadata": { "ParamSize": 243, "ParamBytes": 962794624.0, "BitsPerParam": 4.500674338286857 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 50332672, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 49153, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50332672, "byteOffset": 0 } ], "md5sum": "5680fbff4b12841fd4e4e41d08940605" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 32510080, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 49153, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291584, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 6291584 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 6295680 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14684288 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15732864 } ], "md5sum": "73a60665e7092b5c8f4d053957d0cc51" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "61ec37da805554458504b6198029a73d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 32522240, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 2101248 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 8392704 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9179136 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 11276288 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11538432 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11542528 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19931136 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23076864 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23080960 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 29372416 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30158848 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 32256000 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32518144 } ], "md5sum": "6415b4db64a1b9d3b480554c5414ce55" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "3df0f6ab34d99efa67d2d2f26a6f4362" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "4c29978928a7ae888b6a1457486b1e7e" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "161ec9c6b73d20d6ba50500da39f0104" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "a74454c9bbc3f28b82be0259b39b4abf" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "bebe4fd23af50b76a0295fa5f263f678" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "493424d5e90c78b82b9886a1c48ed407" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "b42e7331dee70afcf8367a642c9b1f58" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "939d292794ea0eef1cad4524f05c3625" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "940959bdba60d26f96615ec663e6414f" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "c8d2a464326ce2916cf0ddb9fcc4c9fe" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "2423a2295f151f1ad1405ac5ccb8529c" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "b372903fcf5de905a1d105729b0b3cd5" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "958f05bd505016ab80ebe21087dac93f" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "b009cf1ce6ccb0a47480460b08769132" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "33857a1b7808aadc2abaf0d950480ca8" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "93d25328fd55d2d3273a6229bd53bc10" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "ebc998504077db19f449352aae04ad8f" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "8c57f6562798d9686cf0de03b9b56d49" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "70eb00ae79828d462a17a88204cf71c4" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "358ffd169a221af74ad715d37a9e7e2f" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "44c53f7689d05d76a02972339490a02d" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "1de5b9ec90d47b6e9ff1b5b60b240d72" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "4c5b81c89ab4f8392ba936af237316d7" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "c50817b48169589511545ad7e35bae12" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "6547ec313065fa6a9f8b4dbb8ba98639" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "3edc48a9b576fe806976229927d9b7da" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "3ffc730581243271a37de7a889691cc1" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "964759b866dc28dc07ebb495c0b5efc7" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "cbf93f96115ff5c5d42bfba31efba156" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "0799e039739e4911d9c081ab8d111ce6" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "6339180a68b6c3e810cc5c3c9bedd9f8" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 256, 16384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "238ab4891a22b67bd878718ab37304bf" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1024, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 256, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 64, 16384 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "ff9d4aa7688ac3cdc5191e0b37e1cde7" } ] }