diff --git a/.gitattributes b/.gitattributes index 70898625f0e2789ba55c622119da6ebc985092e6..28b0217abf662dafdb4409aa71e39e969b3c3463 100644 --- a/.gitattributes +++ b/.gitattributes @@ -123,77 +123,3 @@ DeepSeek-R1-Distill-Qwen-32B_float16/model-00013-of-00013.safetensors filter=lfs DeepSeek-R1-Distill-Qwen-32B_float16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text DeepSeek-R1-Distill-Qwen-32B_float16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text DeepSeek-R1-Distill-Qwen-32B_float16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text -DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/config.json rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00001-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00001-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00001-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00002-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00002-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00002-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00003-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model-00003-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model-00003-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-2,6_mixed/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_2,6_mixed/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/config.json rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00001-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00001-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00001-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00002-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00002-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00002-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00003-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model-00003-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model-00003-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,4_mixed/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_3,4_mixed/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/config.json rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00001-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00001-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00001-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00002-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00002-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00002-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00003-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model-00003-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model-00003-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3,6_mixed/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_3,6_mixed/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/config.json b/DeepSeek-R1-Distill-Qwen-32B_3bit/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/config.json rename to DeepSeek-R1-Distill-Qwen-32B_3bit/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3bit/model-00001-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/model-00001-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3bit/model-00001-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3bit/model-00002-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/model-00002-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3bit/model-00002-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors b/DeepSeek-R1-Distill-Qwen-32B_3bit/model-00003-of-00003.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/model-00003-of-00003.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_3bit/model-00003-of-00003.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_3bit/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_3bit/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_3bit/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_3bit/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_3bit/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_3bit/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_3bit/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-3bit/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_3bit/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/config.json rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00001-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00001-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00001-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00002-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00002-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00002-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00003-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00003-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00003-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00004-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model-00004-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model-00004-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,6_mixed/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_4,6_mixed/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/config.json rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00001-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00001-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00001-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00002-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00002-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00002-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00003-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00003-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00003-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00004-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model-00004-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model-00004-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4,8_mixed/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_4,8_mixed/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/config.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/config.json rename to DeepSeek-R1-Distill-Qwen-32B_4bit/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00001-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00001-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00001-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00002-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00002-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00002-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00003-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00003-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00003-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors b/DeepSeek-R1-Distill-Qwen-32B_4bit/model-00004-of-00004.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model-00004-of-00004.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model-00004-of-00004.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_4bit/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_4bit/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-4bit/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_4bit/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/config.json b/DeepSeek-R1-Distill-Qwen-32B_6bit/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/config.json rename to DeepSeek-R1-Distill-Qwen-32B_6bit/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B_6bit/model-00001-of-00006.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model-00001-of-00006.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model-00001-of-00006.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B_6bit/model-00002-of-00006.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model-00002-of-00006.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model-00002-of-00006.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B_6bit/model-00003-of-00006.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model-00003-of-00006.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model-00003-of-00006.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B_6bit/model-00004-of-00006.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model-00004-of-00006.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model-00004-of-00006.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B_6bit/model-00005-of-00006.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model-00005-of-00006.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model-00005-of-00006.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors b/DeepSeek-R1-Distill-Qwen-32B_6bit/model-00006-of-00006.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model-00006-of-00006.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model-00006-of-00006.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_6bit/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_6bit/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_6bit/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_6bit/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_6bit/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_6bit/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_6bit/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-6bit/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_6bit/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/config.json b/DeepSeek-R1-Distill-Qwen-32B_8bit/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/config.json rename to DeepSeek-R1-Distill-Qwen-32B_8bit/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00001-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00001-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00001-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00002-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00002-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00002-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00003-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00003-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00003-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00004-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00004-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00004-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00005-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00005-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00005-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00006-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00006-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00006-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors b/DeepSeek-R1-Distill-Qwen-32B_8bit/model-00007-of-00007.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model-00007-of-00007.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model-00007-of-00007.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_8bit/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_8bit/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_8bit/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_8bit/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_8bit/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_8bit/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_8bit/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-8bit/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_8bit/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/config.json rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00001-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00001-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00001-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00002-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00002-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00002-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00003-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00003-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00003-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00004-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00004-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00004-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00005-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00005-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00005-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00006-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00006-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00006-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00007-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00007-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00007-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00008-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00008-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00008-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00009-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00009-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00009-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00010-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00010-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00010-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00011-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00011-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00011-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00012-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00012-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00012-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00013-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model-00013-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model-00013-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-bfloat16/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_bfloat16/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/config.json b/DeepSeek-R1-Distill-Qwen-32B_float16/config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/config.json rename to DeepSeek-R1-Distill-Qwen-32B_float16/config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00001-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00001-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00001-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00002-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00002-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00002-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00003-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00003-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00003-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00004-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00004-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00004-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00005-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00005-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00005-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00006-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00006-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00006-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00007-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00007-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00007-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00008-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00008-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00008-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00009-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00009-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00009-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00010-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00010-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00010-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00011-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00011-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00011-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00012-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00012-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00012-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float16/model-00013-of-00013.safetensors similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model-00013-of-00013.safetensors rename to DeepSeek-R1-Distill-Qwen-32B_float16/model-00013-of-00013.safetensors diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_float16/model.safetensors.index.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/model.safetensors.index.json rename to DeepSeek-R1-Distill-Qwen-32B_float16/model.safetensors.index.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_float16/special_tokens_map.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/special_tokens_map.json rename to DeepSeek-R1-Distill-Qwen-32B_float16/special_tokens_map.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_float16/tokenizer.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer.json rename to DeepSeek-R1-Distill-Qwen-32B_float16/tokenizer.json diff --git a/DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_float16/tokenizer_config.json similarity index 100% rename from DeepSeek-R1-Distill-Qwen-32B-float16/tokenizer_config.json rename to DeepSeek-R1-Distill-Qwen-32B_float16/tokenizer_config.json diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/config.json b/DeepSeek-R1-Distill-Qwen-32B_float32/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e95cadc68ad8595dd9b2c7a5e90ab983db75aa35 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.43.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00001-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00001-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c08be18d1a08dfe2e88cc622d2e2cf39466ae410 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00001-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599f4182010f7163917314ab9708c0dcf8589376532d3f1757613b8576be7c64 +size 5316380884 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00002-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00002-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d7722f1c901bcc73f99a2ce1722768ead11cc10 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00002-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47eeb3ad6e5006f9b8e24e4419510fb7d8a925227804de6fbacc8b7f124e962d +size 5033307042 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00003-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00003-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1af7a5a25082cff1c5159548ecd47a842554ab46 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00003-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0409f02c9c0a0a0082925ef55b6bc02c3292edbf37e06f9da19d1cb04771862c +size 5285035904 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00004-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00004-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..127637c46776ec9a83bbbeeebd111ae51f75e126 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00004-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b379576c295ce95268d4d7279f89cda8ccb8a3326b7145c4f465885c9341c607 +size 5285035904 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00005-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00005-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd1de85cde22d2b9500dc129c8d0aff1e5ea4bd9 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00005-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85769e1f3aee11311e9372bad6c0c67a479af4f003c49c901069792dc55d069 +size 5033307043 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00006-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00006-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af6c3919f82bae2bcacc7fab7c5a8721b2649926 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00006-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78eba76c8bb6ca1f6217a5bf22ea8d3e8209b50af025264192a32518efa201fe +size 5285035955 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00007-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00007-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfd68e6c973eeccba728198a158843c63c46b7f4 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00007-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6986251aa1f42f4c827e846d1555fb228ba0057a4810c9a5c9e6ed3082948f8 +size 5285035957 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00008-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00008-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..429a5bd7897d02ffeaf25ddf27d006aa9525ef72 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00008-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad1b8f9274527410211d768ba547c8314ab9809ce641daa42680b92f211190a +size 5033307054 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00009-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00009-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f93c2d47657793c4d69f63477a8894b47898eefd --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00009-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ab10f5e8fb85d354a961a1f7fb210b30693e520ed7c9be534e45230aecbd26 +size 5285035933 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00010-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00010-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f196931524c657311d0679429ae193c34cac488b --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00010-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9516bef4e284800bfeb870db94c5e42531945263a276209b370707419719a8c0 +size 5285035921 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00011-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00011-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..521746e9acd7f9a60b6ec2535a35af332b85adf1 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00011-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b339603f6d23ec6694e1fefc585d551d558991058cdcc719794c1089f9d9bc63 +size 5033307064 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00012-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00012-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..43af56d63a68cc4cd4c9aafe5f5f73eaea969950 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00012-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be3cdcc0529920ff8d27ecfbe3e6e39db020c33097b29837eab88f973e2d3a1 +size 5285035957 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00013-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00013-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0cf97706f52896ab5d9af6b79fd256806badc8b --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00013-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af917c0848b5137c39162d81438110f8fc0dce5fc98b757206ea8666b1e4eb1 +size 5285035955 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00014-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00014-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b13559e7588abb7d261840f1cb3b0d6bf737a6d3 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00014-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7874ace3d18755d37d37a31a0cb8ec02a132b19e55fac2994a51f39a402ad95 +size 5033307064 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00015-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00015-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f14232330e67fc922186ceb92d22ac2c2a4773b9 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00015-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a8eb4f42009b4f765231fb5fd1cb41626703f94ac9005b60a1f386c4c4639af +size 5285035959 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00016-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00016-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fa4182c7a4edd75bf8279b781a2fb1198d6332d --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00016-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cbdbd494345f6e19f2498652fdae9a974a3ad1201bcfcd49ce48030c94d3d98 +size 5285035947 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00017-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00017-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b140efc4ca5bf71fa459b55b9b7c278e866a08a7 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00017-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3497b33ece845f5d2db9b23fe817e80021dd1b4aefebf75cfd690412736264cb +size 5033307066 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00018-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00018-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f146ce3809c2bab9b308e8aa9d2f01fc4ad4dc3 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00018-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3260bfe6b9a11908e1ce3d2de925bbef772663098efac11238d22f2e37c125d1 +size 5285035951 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00019-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00019-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..293d307c478d7b89aff444d40e6201c1d8899eec --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00019-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf1b2c2f3b32b94eb3d35d5f258396c18b4622e99cf07e4055de5fd1e9b41cd +size 5285035951 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00020-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00020-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b6f9b7c78d0a2b4e3e51838449c9b2f20ec8243 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00020-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101a930280a84deb5427b4a44187d21951cdafe23f325f4bc9cbb82e8e89872c +size 5033307062 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00021-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00021-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea781910d95acaa567c1f367391fbed8315c0aea --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00021-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f9ad4887e00f8b1ccdd4546e2284f3fef2c2dfae14f0dee1bc8a0dc8a7d2d9 +size 5285035953 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00022-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00022-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b003c1660eebdfead72bd9b665657676f46ee62 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00022-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65bcd5546efa4fa235ecabba608fb37a3373799b144ad72b9679c9424ed8621a +size 5285035951 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00023-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00023-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd36555b51b93f7ab41143f65b0d1bf089d529f7 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00023-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45295477662fc652e1622c71a5e46ceb72d602f4efdcfea91c7b505142186047 +size 5033307064 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00024-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00024-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1460f3b4bb5f702af963a7e27eefe880daf1cf5 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00024-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db901135200cd1fb7e68c459fb2d55fb947d62c343200cf19775836b80b76b2 +size 5285035957 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00025-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00025-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70b1f7a0d925dd61437b6714dd4fa739dd2145ff --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00025-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53e2e2e2f3a9546c36324e9d86ecf5abb2ffddb22a6a214347014cbac9c4790 +size 3082946433 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model-00026-of-00026.safetensors b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00026-of-00026.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7484c3ec7d515ceeffe230cedd92fef66ef4f39c --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model-00026-of-00026.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcf7e822eea946c5e9b15667b7ac601dd6fc8f4f146ddf84cbb18a4c5447991 +size 3114270846 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/model.safetensors.index.json b/DeepSeek-R1-Distill-Qwen-32B_float32/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..4b0ff3b60e4cd73ae34bbdc4cf4555c373f16c13 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/model.safetensors.index.json @@ -0,0 +1,778 @@ +{ + "metadata": { + "total_size": 131055505408 + }, + "weight_map": { + "lm_head.weight": "model-00026-of-00026.safetensors", + "model.embed_tokens.weight": "model-00001-of-00026.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00026.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00026.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00026.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00026.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00026.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00026.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00026.safetensors", + "model.layers.10.input_layernorm.weight": "model-00005-of-00026.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00026.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00026.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00026.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00026.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00026.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.12.input_layernorm.weight": "model-00006-of-00026.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00026.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.14.input_layernorm.weight": "model-00007-of-00026.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00026.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00026.safetensors", + "model.layers.15.input_layernorm.weight": "model-00007-of-00026.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.input_layernorm.weight": "model-00007-of-00026.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.17.input_layernorm.weight": "model-00008-of-00026.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00026.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00026.safetensors", + "model.layers.18.input_layernorm.weight": "model-00008-of-00026.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00026.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.19.input_layernorm.weight": "model-00009-of-00026.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00026.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00026.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00026.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00026.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00026.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00026.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.20.input_layernorm.weight": "model-00009-of-00026.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.input_layernorm.weight": "model-00009-of-00026.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.22.input_layernorm.weight": "model-00010-of-00026.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00026.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00026.safetensors", + "model.layers.23.input_layernorm.weight": "model-00010-of-00026.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.input_layernorm.weight": "model-00010-of-00026.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.25.input_layernorm.weight": "model-00011-of-00026.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00010-of-00026.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00026.safetensors", + "model.layers.26.input_layernorm.weight": "model-00011-of-00026.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00026.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.27.input_layernorm.weight": "model-00012-of-00026.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00026.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00026.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00026.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00026.safetensors", + "model.layers.28.input_layernorm.weight": "model-00012-of-00026.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.input_layernorm.weight": "model-00012-of-00026.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00026.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00026.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00026.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00026.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00026.safetensors", + "model.layers.30.input_layernorm.weight": "model-00013-of-00026.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00012-of-00026.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00026.safetensors", + "model.layers.31.input_layernorm.weight": "model-00013-of-00026.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.input_layernorm.weight": "model-00013-of-00026.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.33.input_layernorm.weight": "model-00014-of-00026.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00026.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00026.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00026.safetensors", + "model.layers.34.input_layernorm.weight": "model-00014-of-00026.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00014-of-00026.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.35.input_layernorm.weight": "model-00015-of-00026.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00026.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00026.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00026.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00026.safetensors", + "model.layers.36.input_layernorm.weight": "model-00015-of-00026.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.input_layernorm.weight": "model-00015-of-00026.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.38.input_layernorm.weight": "model-00016-of-00026.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00015-of-00026.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00026.safetensors", + "model.layers.39.input_layernorm.weight": "model-00016-of-00026.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00026.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.40.input_layernorm.weight": "model-00016-of-00026.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.41.input_layernorm.weight": "model-00017-of-00026.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00016-of-00026.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00026.safetensors", + "model.layers.42.input_layernorm.weight": "model-00017-of-00026.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00017-of-00026.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.43.input_layernorm.weight": "model-00018-of-00026.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00017-of-00026.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00017-of-00026.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00017-of-00026.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00026.safetensors", + "model.layers.44.input_layernorm.weight": "model-00018-of-00026.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.input_layernorm.weight": "model-00018-of-00026.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.46.input_layernorm.weight": "model-00019-of-00026.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00018-of-00026.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00026.safetensors", + "model.layers.47.input_layernorm.weight": "model-00019-of-00026.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.input_layernorm.weight": "model-00019-of-00026.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.49.input_layernorm.weight": "model-00020-of-00026.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00019-of-00026.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00026.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00026.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.50.input_layernorm.weight": "model-00020-of-00026.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00020-of-00026.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.51.input_layernorm.weight": "model-00021-of-00026.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00020-of-00026.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00020-of-00026.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00020-of-00026.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00020-of-00026.safetensors", + "model.layers.52.input_layernorm.weight": "model-00021-of-00026.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.input_layernorm.weight": "model-00021-of-00026.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.54.input_layernorm.weight": "model-00022-of-00026.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00021-of-00026.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00021-of-00026.safetensors", + "model.layers.55.input_layernorm.weight": "model-00022-of-00026.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.input_layernorm.weight": "model-00022-of-00026.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.57.input_layernorm.weight": "model-00023-of-00026.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00022-of-00026.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00026.safetensors", + "model.layers.58.input_layernorm.weight": "model-00023-of-00026.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00023-of-00026.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.59.input_layernorm.weight": "model-00024-of-00026.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00023-of-00026.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00023-of-00026.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00023-of-00026.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00023-of-00026.safetensors", + "model.layers.6.input_layernorm.weight": "model-00004-of-00026.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00026.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00026.safetensors", + "model.layers.60.input_layernorm.weight": "model-00024-of-00026.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.input_layernorm.weight": "model-00024-of-00026.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.62.input_layernorm.weight": "model-00025-of-00026.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00024-of-00026.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00024-of-00026.safetensors", + "model.layers.63.input_layernorm.weight": "model-00025-of-00026.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00025-of-00026.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00025-of-00026.safetensors", + "model.layers.7.input_layernorm.weight": "model-00004-of-00026.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00026.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00026.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00005-of-00026.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00026.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00026.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00026.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00026.safetensors", + "model.norm.weight": "model-00025-of-00026.safetensors" + } +} \ No newline at end of file diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/special_tokens_map.json b/DeepSeek-R1-Distill-Qwen-32B_float32/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer.json b/DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer_config.json b/DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ef6e98c3e0446cad00c5e6fb6bf2f5bbaf2eb0bd --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-32B_float32/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/README.md b/README.md index 8c87f6c865632c1f3eb5107c43f927f3934303a8..c5a73cc97e0b7f963ae28864ffdc177c996fdee1 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,7 @@ --- quantized_by: sealad886 -license_link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE +license_link: >- + https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE language: - en pipeline_tag: text-generation @@ -8,7 +9,7 @@ base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B tags: - chat - mlx -- conversations +license: mit --- # mlx-community/DeepSeek-R1-Distill-Qwen-32B @@ -42,6 +43,7 @@ The model conversion uses a range of quantization configurations defined via `ml Converts the model to a different floating point precision without quantizing weights. - **bfloat16:** Model converted to bfloat16 precision. - **float16:** Model converted to float16 precision. + - **float32:** Model converted to float32 precision. ## Use with mlx