{ "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": "98091ef8425b9cc19914d103a34063a7" }, { "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": "15bf88a1b973224bd8f3585669e4c2af" }, { "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": "65d1e78a428092bb23e0b14643119c42" }, { "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": "c385f772a7c9a1949bba1b97002d53c6" }, { "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": "0687787ef407e6d340234316a66b3182" }, { "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": "d381d7e877d385acb32cd11884998a28" }, { "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": "a0e31fb9b371763e41c1462ba37e21ae" }, { "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": "ac664a00ce1442b4a120515b8101e023" }, { "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": "7372818369df6d28c782a103699ff6ae" }, { "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": "06cf7d6d4ff6967a7223b5394903aa74" }, { "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": "672c500b16b21b9e8d8a62867a0d93e4" }, { "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": "55ac193b9418e96fb8f2440f6d264a88" }, { "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": "2953ff310ceb7489e2f97115db40dfcf" }, { "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": "2fa0d0536c81bf2a73d9e161232ce9aa" }, { "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": "48c5373960d64f81fa490416a0e46d8d" }, { "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": "a07333911dac7294278e82875af66609" }, { "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": "8b5c5798043bf42d96dd0f5c32ecc3b4" }, { "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": "27e3dc3785dbc0553fedfc195238001d" }, { "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": "f2ad9be2a58f4b8eb7168e701818844e" }, { "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": "e66507362d0c05066b1ffea774258e84" }, { "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": "14e5f6a42d14ccb68bf1f8c5578130af" }, { "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": "89836e2081274d87bfec49c3a21edb55" }, { "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": "308b1c62e16c82a6a0689a6288c0abaa" }, { "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": "08ff823e3b057e8bf77edcd5a350eaf7" }, { "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": "61ae695981354e7b8d83515cc8b028eb" }, { "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": "34e4592b0773d6fe7785a37d4031d54e" }, { "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": "0c7ecf6cd96741df3d9b7744abc4fd51" }, { "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": "0f41426662c406be6052381e02752ca9" } ] }