diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,3577 @@ +{ + "metadata": { + "ParamSize": 311, + "ParamBytes": 1670769664.0, + "BitsPerParam": 7.5213817841322435 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 466747392, + "records": [ + { + "name": "lm_head.weight", + "shape": [ + 151936, + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 466747392, + "byteOffset": 0 + } + ], + "md5sum": "4004155c68c07080f39231f289b9c9d3" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 466747392, + "records": [ + { + "name": "model.embed_tokens.weight", + "shape": [ + 151936, + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 466747392, + "byteOffset": 0 + } + ], + "md5sum": "4004155c68c07080f39231f289b9c9d3" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 33215488, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 3072 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 6884352 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 7744512 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 21507072 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 23227392 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 23230464 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 23234560 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 196608, + "byteOffset": 24807424 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 25004032 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26183680 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 26331136 + }, + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 26334208 + } + ], + "md5sum": "96f14bf184f59882dd10f3d4c3ea85bd" + }, + { + "dataPath": "params_shard_3.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": "04c9da0d70f25499b79f8fab09666943" + }, + { + "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": "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": "ad9460adedd407cc42ba16e2784f4c6e" + }, + { + "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": "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": "d85d2b84cf839262fc721e4f4877cb96" + }, + { + "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": "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": "408999b8cf78dcf666231748612b1099" + }, + { + "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": "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": "092c948b8fb793ff47506f336d2579ea" + }, + { + "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": "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": "2ba1e5da395d6a45c176f483ed1dc3e5" + }, + { + "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": "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": "b0d2a8d5b25dbc95bfec3c4cdc8e8c63" + }, + { + "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": "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": "8b0ed6b3af68d5c2bcedab1a67cacc45" + }, + { + "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": "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": "968fce365c650d2c0ed0f9d119205da8" + }, + { + "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": "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": "6b8880c84f0e46a3a41a3ee5c5f1d046" + }, + { + "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": "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": "a3103d14f948ab251baa4a2258cbcdec" + }, + { + "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": "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": "b5333047eda56ee465327c1621b5c254" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 32349184, + "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.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 18586624 + } + ], + "md5sum": "cfe4093d7cee62a92b6abeb60c7418f7" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 31155200, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 0 + }, + { + "name": "model.layers.21.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 1720320 + }, + { + "name": "model.layers.21.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 1724416 + }, + { + "name": "model.layers.21.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 196608, + "byteOffset": 3297280 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 3493888 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 4673536 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 4820992 + }, + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 4824064 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 11705344 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 12565504 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 26328064 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 28048384 + }, + { + "name": "model.layers.3.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 28051456 + }, + { + "name": "model.layers.3.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 28055552 + }, + { + "name": "model.layers.3.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 196608, + "byteOffset": 29628416 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 29825024 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 31004672 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 31152128 + } + ], + "md5sum": "ffa9e80a69797b28f47153360db14b0f" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 33212416, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 0 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 6881280 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 7741440 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 21504000 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 23224320 + }, + { + "name": "model.layers.4.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 23227392 + }, + { + "name": "model.layers.4.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 23231488 + }, + { + "name": "model.layers.4.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 196608, + "byteOffset": 24804352 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 25000960 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26180608 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 26328064 + }, + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 26331136 + } + ], + "md5sum": "013792b790c1fcd7c5badca62904a8af" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 27191296, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 0 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 860160 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 14622720 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 16343040 + }, + { + "name": "model.layers.5.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 16346112 + }, + { + "name": "model.layers.5.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 16350208 + }, + { + "name": "model.layers.5.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 196608, + "byteOffset": 17923072 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 18119680 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 19299328 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 19446784 + }, + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 19449856 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 26331136 + } + ], + "md5sum": "99fdda0592a9a154a782bca25f055ed3" + }, + { + "dataPath": "params_shard_19.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": "75431679e429e9574566c4233c04880c" + }, + { + "dataPath": "params_shard_20.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": "25611da62e0649478747ceec3582a944" + }, + { + "dataPath": "params_shard_21.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": "a8e417eaddde0408eb5d41b43b7db70c" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 33218560, + "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.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 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 26331136 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 26334208 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 26337280 + } + ], + "md5sum": "2842faaa26a92524d37086347108fcd5" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 27191296, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 0 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 17920, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 13762560, + "byteOffset": 860160 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 17920, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 14622720 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 16343040 + }, + { + "name": "model.layers.22.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 16346112 + }, + { + "name": "model.layers.22.self_attn.c_attn.q_weight", + "shape": [ + 2048, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 16350208 + }, + { + "name": "model.layers.22.self_attn.c_attn.q_scale", + "shape": [ + 2048, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 196608, + "byteOffset": 17923072 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 1536, + 192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 1179648, + "byteOffset": 18119680 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 1536, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 19299328 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 19446784 + }, + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 1536, + 1120 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6881280, + "byteOffset": 19449856 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 1536, + 280 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 26331136 + } + ], + "md5sum": "499b0d44d8091c5ee997d3a1475c5d3e" + }, + { + "dataPath": "params_shard_24.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": "689a7f1b3256cdf4e07be9b352e53c80" + }, + { + "dataPath": "params_shard_25.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": "4dbb4691b7dd0c16db5e37a35e050f84" + }, + { + "dataPath": "params_shard_26.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": "ed102401b66e1ed1d2143818f8422d8a" + }, + { + "dataPath": "params_shard_27.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": "dc16470e62524d88ca09c3976b68dcdc" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 18589696, + "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.norm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 18586624 + } + ], + "md5sum": "806be520dcd19047bbf8ef0c06e0a1bd" + } + ] +} \ No newline at end of file