{ "metadata": { "ParamSize": 163, "ParamBytes": 695245056.0, "BitsPerParam": 4.500628907887781 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131336192, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128258, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131336192, "byteOffset": 0 } ], "md5sum": "6124bad0e973c9ca2eb02850856705b9" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "73428a8effc04d761eed7840fdf6b8c7" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 31498496, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128258, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16417024, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 16417024 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 16421120 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 24809728 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 25858304 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 27955456 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 27959552 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31105280 } ], "md5sum": "a857d6062df7e6034a3f00428a6eba4a" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "35880f151a0320540423f6a56b0e39b0" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "0399e7018251ef272ce9e454be12e330" }, { "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": "d16e6c34f09f4a237b34a03bb76865df" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "89a1adc7f1d1810c4676d17d0438d17c" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31854592, "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": "float16", "format": "f32-to-bf16", "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": "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 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28315648 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "580e966efc6dccccff02143a3ac6ea93" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "5d0ff86eb3582a01fc5cc8ff05994bac" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "1069869e7d8fc765ba31c9b2649c7e97" }, { "dataPath": "params_shard_10.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": "40bdf3661bdbdf6287d8e6b384a8106b" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "99b309c374b5fcd2fa939c6823f16719" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31854592, "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": "float16", "format": "f32-to-bf16", "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": "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 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28315648 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "cb9bd7c0736545c9df8195c45184af09" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "ad094798695790f88b895530893f4026" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "607563464d8a59cae7c60da0950c56a0" }, { "dataPath": "params_shard_15.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": "b86b212a485e75ab5577f7fce6f0e891" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "c88417f337ecbaeb8a7ac02535e9c5a1" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31854592, "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": "float16", "format": "f32-to-bf16", "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": "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 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28315648 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 31461376 } ], "md5sum": "4ceff3c4fa259163a596f446a34bfa90" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30679040, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2359296 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2363392 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 10752000 }, { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11800576 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28577792 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30674944 } ], "md5sum": "ad8d370c9603a4cb7a23e17b3d8df3b7" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 32116736, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 3145728 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 3538944 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5636096 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5898240 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 5902336 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 14290944 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15339520 } ], "md5sum": "23b562f2a370825fae321c560bb522b8" }, { "dataPath": "params_shard_20.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": "d4f7772740d5b196b4edb2389b91bfc1" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25444352, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 2101248 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 5246976 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 5640192 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 7737344 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 7999488 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8003584 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 16392192 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17440768 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19537920 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 19542016 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 3072, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 393216, "byteOffset": 22687744 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23080960 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 25178112 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25440256 } ], "md5sum": "af26897b30f986377a5cb178c8b1c09f" } ] }