diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,3615 @@ +{ + "metadata": { + "ParamSize": 313, + "ParamBytes": 999820288.0, + "BitsPerParam": 4.500937659812007 + }, + "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": "f5deae0fcd34d27eab8c21a024c8f711" + }, + { + "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": "accc7a495594768625d8469380130b72" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 29174784, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 151936, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14585856, + "byteOffset": 0 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 151936, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14585856, + "byteOffset": 14585856 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 29171712 + } + ], + "md5sum": "ae1dfada404728dce402091f4401ccd4" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 21504000 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 23224320 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26180608 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "1820f3fd356105d481dd8b01eea1915f" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 27191296, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 14622720 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 16343040 + }, + { + "name": "model.layers.1.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 19299328 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 26331136 + } + ], + "md5sum": "8a33e6af3a9e36d80c960b9f39589377" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.10.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "c1c00d4d1226da4dc6582a63544f0be7" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.11.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "629c77a93182ba528f7f574c27a5041e" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.12.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "e876ced97d9e24ff194706ed53c38285" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.13.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "586c54e5d27ef3e1cbc487be2394f0fa" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.14.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "433c3d6ba4414e15f1ff7887f6f7a6dc" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.15.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "5a34b349cdad1743ac9c04a6789318c5" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.16.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "213b770ec9caae8a16b988edac1052c9" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.17.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "1060d21c45674e009aa882fdfa733e97" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.18.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "909cc35a4c07aab9afeb35a1c234a94b" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.19.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "87be97d87ef2698d37068226731c3994" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.2.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "71f068ccd14d34ece134254f1526a3d2" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.20.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "813b3227b3a80948174130d6df4d2cf5" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.21.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "52d232883cc6c86ed14d4bef6d5589eb" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.22.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "58f131fa9e510407fc7b0a97c21553da" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.23.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "3db48f9483ae44df502d9e82f00195b3" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.24.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "f424198c22c3891fa09298641c764185" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.25.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "07dab1c18a55c464ef6b21c36f00bc64" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.26.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "44c0bf0e631e366ba490b6ea9c548bef" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.27.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "dfd5f83222f16e21e6d52fbf1fd7b000" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.3.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "84afd98a1578859faf792451e46cb8af" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.4.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "e80fb8e1b3c747052052742c76b1062d" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.5.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "99d116b46fdb2df517ad5e6ba222ae51" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.6.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "6e72108d5d3e46b06a1caae71c7f36a9" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.7.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "fb5d17d4e512b052b49fd8ab7c852b5b" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.8.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "8d4e6597b7773c2d20af82e5d4a11844" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.9.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.norm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 18586624 + } + ], + "md5sum": "f2f4c5c3d83aaa1d953bcc146de45dcf" + } + ] +} \ No newline at end of file