mobiuslabsgmbh
/

DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0

Text Generation

Model card Files Files and versions Community

mobicham commited on 7 days ago

Commit

1032f38

·

verified ·

1 Parent(s): 2edfda3

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ This is a version of the <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1
 ## Performance
-| Models            | <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B">DeepSeek-R1-Distill-Qwen-1.5B</a> | <a href="https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0">DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1</a> |
 |:-------------------:|:--------:|:----------------:|
 | ARC (25-shot)      | 40.96 | <b>41.3</b>  |
 | HellaSwag (10-shot)| 44    | <b>45.22</b> |
@@ -18,7 +18,7 @@ This is a version of the <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1
 | GSM8K (5-shot)     | 69.9  | <b>73.24</b> |
 | Average            | 49.13 | <b>50.86</b> |
-| Models            | <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B">DeepSeek-R1-Distill-Qwen-1.5B</a> | <a href="https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0">DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1</a>  |
 |:-------------------:|:--------:|:----------------:|
 | GPQA (0-shot)     | 26.96 | <b>27.8</b>  |
 | MMLU PRO (5-shot) | 16.74 | <b>19.44</b> |

 ## Performance
+| Models            | <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B">DeepSeek-R1-Distill-Qwen-1.5B</a> | <a href="https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0">DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0</a> |
 |:-------------------:|:--------:|:----------------:|
 | ARC (25-shot)      | 40.96 | <b>41.3</b>  |
 | HellaSwag (10-shot)| 44    | <b>45.22</b> |
 | GSM8K (5-shot)     | 69.9  | <b>73.24</b> |
 | Average            | 49.13 | <b>50.86</b> |
+| Models            | <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B">DeepSeek-R1-Distill-Qwen-1.5B</a> | <a href="https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0">DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0</a>  |
 |:-------------------:|:--------:|:----------------:|
 | GPQA (0-shot)     | 26.96 | <b>27.8</b>  |
 | MMLU PRO (5-shot) | 16.74 | <b>19.44</b> |