{ "metadata": { "ParamSize": 313, "ParamBytes": 1111169024.0, "BitsPerParam": 5.002201462167321 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 116686848, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 116686848, "byteOffset": 0 } ], "md5sum": "3eba7944239eea590b63e87f00016a6b" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 116686848, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 116686848, "byteOffset": 0 } ], "md5sum": "be8d442fc5234135620521550a8148fa" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 29174784, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14585856, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14585856, "byteOffset": 14585856 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 29171712 } ], "md5sum": "51e65235b4e65bd14f51a603e8ef7b49" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33212416, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 6881280 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 7741440 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 21504000 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23227392 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23231488 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 24804352 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25000960 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 26180608 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 26328064 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 26331136 } ], "md5sum": "59cea6a143c3e50522e6a7ab56fd1302" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 27191296, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 860160 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 14622720 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 16343040 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 16346112 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 16350208 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17923072 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 18119680 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 19299328 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 19446784 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 19449856 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 26331136 } ], "md5sum": "13283f546f5e1640e0d179f91c737060" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f80a070c11451222f8169d453336a19c" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "114d2917404e99a37c39aacfa57a9a50" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "dc3b5e347d2aba0026bc6cc0dcf4b005" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "60e7284515bb4c2999432289d45839c4" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f48e561b8d2b76519c23c5db3e8f6f16" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "252c5013974cfddd0dbba30e029f877e" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "390cb82a590d93b12129b8d3c50f73f1" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "a3495d635ea3c53c9b0bbbcef749ceb8" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "35700f4804c01da98c6241cee2ff5732" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "fc44a49e8c67d1e47c7d9f9b47c32cb5" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "66952571c7809812a74701771112d5ac" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "451ddd6918f481774a5ddcae93fcc19a" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "6d6e530a4f2c516481ef459c432eab73" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "0e25e76a52534e27e009f1966b60e908" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "0b2f3521eb647a178bf4fe69ebbefca4" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "176c5666e37994d7f23960de639e90cc" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "ceb962974aa3ffd06a616a6c52270097" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "ab9d7f443673b7890cfbf49008594ab9" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "61f19df02bf82992f18b0a6ec1370776" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "9bd46c03febaca7936dd5c670e87c9db" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "a967b6249d494149ba4d36888fb580be" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "c456c605796669a1a035b5509af8b906" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "4932c078feff0216f175050579e08a9a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "8686b64ff10449b640afc32ed7439a65" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "037698a9234e2d563a950ced66a97bf3" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 18589696, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 } ], "md5sum": "e5c2ee400f5502dbba790e85967f0990" } ] }