diff --git "a/tensor-cache.json" "b/tensor-cache.json" new file mode 100644--- /dev/null +++ "b/tensor-cache.json" @@ -0,0 +1,3577 @@ +{ + "metadata": { + "ParamSize": 311, + "ParamBytes": 868547584.0, + "BitsPerParam": 4.501079412165634 + }, + "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": "3d843cc512e9ab311fe319cd17534551" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 22330368, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 151936, + 48 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14585856, + "byteOffset": 0 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 21470208 + } + ], + "md5sum": "663cd5091a2c5ab29b5ea2d933263216" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "08c3366af03efb9e36524b8d98259cc9" + }, + { + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 1720320, + "byteOffset": 13762560 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3072, + "byteOffset": 15482880 + }, + { + "name": "model.layers.1.self_attn.c_attn.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 18439168 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 1536 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "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": "float16", + "format": "f32-to-bf16", + "nbytes": 860160, + "byteOffset": 25470976 + } + ], + "md5sum": "433da3fd371e0411f00a0578e1aa0c6e" + }, + { + "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": "a0b8bb6919ddb15b3e1b0b51581e7c2c" + }, + { + "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": "69ce333223ba26009fb3bda7fedaf636" + }, + { + "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": "0db750d61cac54783322d251b8addebd" + }, + { + "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": "1d479ff8a2f77fb5530526a2eba2b2b0" + }, + { + "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": "0078b0d4cd0a6e59735131473223f013" + }, + { + "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": "209457dcef0817c110292d1f6f4edeb4" + }, + { + "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": "f7d53c94261ce0398598974564b5d182" + }, + { + "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": "f93bae1cb149a4ec331447a125b4373e" + }, + { + "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": "85afcb04144072593cf1bfc774baef7a" + }, + { + "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": "92783ecc3b4eea4e107e21814f749972" + }, + { + "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": "04e2115a5a5f6756753d8933b04c4c52" + }, + { + "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": "2cf930c6a179d97b7a037dfb27ae0e40" + }, + { + "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": "f7afa408e78cc69a135a8a855455a77c" + }, + { + "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": "fdbec0a255588e00385fe20e32ff3294" + }, + { + "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": "ce3bb4451117dbf30543123ae389346e" + }, + { + "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": "4b91558489ef519138ff059a7978285b" + }, + { + "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": "ddd52e6fb47b237954bbac7bd44e506d" + }, + { + "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": "417cfdecc4894bc2ee30c2d702aa1f44" + }, + { + "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": "a61e4812b63ccbc076106609cb69ac4e" + }, + { + "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": "9a3b21fd5e1320258b26ee1848490f2e" + }, + { + "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": "c13f2b79c6afd171b716aa9e517b582c" + }, + { + "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": "1ff80b6246bba6ce64744e1eb895a39c" + }, + { + "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": "8994378148ac93ee2e847e88daeb127d" + }, + { + "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": "c38643f0d9e150d73be1a32193f70654" + }, + { + "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": "4341101ddeaee5b212014bd224fde250" + } + ] +} \ No newline at end of file