{ "metadata": { "ParamSize": 269, "ParamBytes": 1148854272.0, "BitsPerParam": 5.003642591223663 }, "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": "0d7d9cbbba4d687c389ce7aa3714f8e3" }, { "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": "dfc78043fe4f97468a031067f8750a2c" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 19447808, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 64 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 19447808, "byteOffset": 0 } ], "md5sum": "6cb78be746129098b34f37c667b257d9" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25792512, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 64 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 19447808, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 25088000 } ], "md5sum": "1801b488427671712d27805272e5f685" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "8157ada8dd04f951b24eaa1889c8d405" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "b815644e61379a79479c5fef226fb2ce" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "494d837e0385da1cb86063d5d6cbb66e" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "8af8b8f1ded44b043bf8f2c00af1259a" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "c37b00c25e6722783bcfb3a9dc654c45" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "4b6d7298c913ba402950b966c3e7aa5a" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "1311238cbb9fd47ec06c3e25b552282f" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "1192b5434d5fd2be62f0949c4d88c3e1" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "c12c81bc7ab887e44b5aa23afbf0be19" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "662a7d85cb7128a218ef157191c6e15e" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "7818c8e352a9e400bba4de79d6e02a0e" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "11ec92d85999e5675653ff1ec2948fc4" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "0e0a77c34052c6eff0fee1a9e668de5b" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "6e4b07f157f394e33b40eecc865b17af" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "6d1f507fb7767e99c3443fff7b1ac0b4" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "f08097e783b2bae528f5d1cfe1d938ef" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "13aa8ba72937fd341592c7e1cb16fc9d" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "5a20da0a0773775203b49cd8c3834046" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "055fb4e13e34b8c3aa11da575b2338ca" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "b0dfcad538d19cf9517ebe6e2e0a83b8" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "1184af33117cbbf4fc5b3fcae8a093c5" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "46de0d329429c4e41a84962cfafba4b0" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 704512, "byteOffset": 27774976 } ], "md5sum": "0c9109bd7d637f4d345da987c3c98a26" }, { "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": "float32", "format": "f32-to-bf16", "nbytes": 1409024, "byteOffset": 11272192 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12681216 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 6144 ], "dtype": "float32", "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": "float32", "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": "float32", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 21872640 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22134784 } ], "md5sum": "23f521649503d15a7d0cece6f0e1a306" } ] }