{ "metadata": { "ParamSize": 269, "ParamBytes": 1033572352.0, "BitsPerParam": 4.501551474039708 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 155582464, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155582464, "byteOffset": 0 } ], "md5sum": "ca3596dc2cfd82c1012d5b81b88f420d" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 155582464, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155582464, "byteOffset": 0 } ], "md5sum": "febe39ab7f97eabe61436e8213d10349" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 19447808, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 19447808, "byteOffset": 0 } ], "md5sum": "895ca8417bf14390b9bde1f7ac6ca9b5" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25792512, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 19447808, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19447808 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 19451904 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 25088000 } ], "md5sum": "98380e1137b82190652d03dc7668385e" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "37e1bc01c5217b1f3178acedf3bad059" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "604b7e5f9034a269308b2fc4a8196a7e" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "6cfbf0980dff7d731e4560ca3b6148f7" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "cd8e32d0882636e335aafb4f39e63b18" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "7afce92ff107ce1f60465a50616555ea" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "b84d536a5148b801508888f5d86d4c5b" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "997106c3537b82c3568faaf4469ddcf2" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "6a6d0672ec0037bb95e044fb1b8ab047" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "7979636cb66265cc990e332f544738a7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "bb9c22c52414a247ea183a196f8fd5ac" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "b2908023183dff566f9394179a4b3ce1" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "26017c4221b033d9bb5a2f705aa2add5" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "933db36f0b5d6a95f4af00cb6b052946" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "d41a4d848724da7c279dbed48d260e03" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "c727bf4873ce4e76941e9bf3fa2dd429" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "278d15d9c68a32b56d2ea10433772d42" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "6d0ecdef5709c0126785f8d5e088c314" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "7c67a66d00b466b07ca2a332dcaa6661" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "2285a5aa1ec3d3495b797612d1d99890" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "65563eb1b3f4363dcb121a77123899ee" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "9394b7aceada4396bc41896bb8c90e74" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "81d6b6a5293556fc488a866583dcdba9" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 28479488, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 688 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22138880 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 172 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "1624d429424fee3c6b8c03aaf4472e2d" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 22138880, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 11008, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 11008, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12685312 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12697600 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 6144, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 18989056 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 19775488 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 } ], "md5sum": "1022f8bc9ab3b2de2a22374b39774e81" } ] }