diff --git "a/ndarray-cache-b16.json" "b/ndarray-cache-b16.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache-b16.json" @@ -0,0 +1,3585 @@ +{ + "metadata": { + "ParamSize": 311, + "ParamBytes": 965310464.0, + "BitsPerParam": 5.002534272041053 + }, + "records": [ + { + "dataPath": "params_shard_0.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": "d6a4315ea780a0261dec50ea468198b0" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 22330368, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 151936, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 14585856, + "byteOffset": 0 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3072, + "byteOffset": 14585856 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 14588928 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 860160, + "byteOffset": 21470208 + } + ], + "md5sum": "a26a387126466fe02ab5b85975ca6a5c" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 26331136, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4096, + "byteOffset": 15485952 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 15490048 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 196608, + "byteOffset": 17062912 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 17259520 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3072, + "byteOffset": 18586624 + }, + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 18589696 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "e4a2ce861bf42975ad50c8cde5812cb6" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 26331136, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.1.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4096, + "byteOffset": 15485952 + }, + { + "name": "model.layers.1.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 15490048 + }, + { + "name": "model.layers.1.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 196608, + "byteOffset": 17062912 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 17259520 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3072, + "byteOffset": 18586624 + }, + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 18589696 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "67c64c3e7b0dca7b64860161602b8482" + }, + { + "dataPath": "params_shard_4.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": "6198be2610cffc271d3ccebc9e657882" + }, + { + "dataPath": "params_shard_5.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": "05e1bcd6a59dbcdf7aed332db3589bcf" + }, + { + "dataPath": "params_shard_6.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": "0602a265f65032107e869987ef13efc3" + }, + { + "dataPath": "params_shard_7.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": "ca9506fec99e3dbe350e817bb51a03ea" + }, + { + "dataPath": "params_shard_8.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": "6b94806ff97a81e9d69354186cd91da1" + }, + { + "dataPath": "params_shard_9.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": "9452acd659acc3fcfa6c1a60128a130e" + }, + { + "dataPath": "params_shard_10.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": "30f66104a529c3c7303fb0b678704a5c" + }, + { + "dataPath": "params_shard_11.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": "12eaf551bef6221bf98bf589b65b3d31" + }, + { + "dataPath": "params_shard_12.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": "5c10f92e4d064cebaa04275e4d145218" + }, + { + "dataPath": "params_shard_13.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": "250bfc0430c639fe0c777d9700f8737d" + }, + { + "dataPath": "params_shard_14.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": "e13e635c922e0fb1bfbddd2dfbd0ca1b" + }, + { + "dataPath": "params_shard_15.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": "4ab4e4b6d7ada42af01c05cd5291b960" + }, + { + "dataPath": "params_shard_16.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": "15ffc5996d1b952a36bc8f54d210b44c" + }, + { + "dataPath": "params_shard_17.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": "feaccc2a82ec07676b39600c51edaace" + }, + { + "dataPath": "params_shard_18.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": "1497fe04008e6f5f1af5ea6a06859f9c" + }, + { + "dataPath": "params_shard_19.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": "cd17e383e7f45cb80ebcd8981123efe4" + }, + { + "dataPath": "params_shard_20.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": "d995a9dd75c251dbcd9fdcf9ad3f5938" + }, + { + "dataPath": "params_shard_21.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": "f6ba3ec3ebb2b641f6d01813eba481f9" + }, + { + "dataPath": "params_shard_22.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": "1b7ecdfcd705cbe12c2f499608755ed8" + }, + { + "dataPath": "params_shard_23.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": "1c02b566893a76eff7db464b85241198" + }, + { + "dataPath": "params_shard_24.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": "881de98cebe050786a5c0cffb1bc3e6b" + }, + { + "dataPath": "params_shard_25.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": "f8300e214ed5e10286c6d0053021e911" + }, + { + "dataPath": "params_shard_26.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": "d111aae7d5b6dd112de78c2aeb409219" + }, + { + "dataPath": "params_shard_27.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": "a10ae979f97ac008c6175e39beaeca37" + }, + { + "dataPath": "params_shard_28.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": "cde0c22d5359bdf41fd1c4d997f66dd7" + }, + { + "dataPath": "params_shard_29.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": "4116507189c695dd192a7de0074c0a0a" + } + ] +} \ No newline at end of file