Adding Evaluation Results

README.md

@@ -103,4 +103,17 @@ There's almost none evaluation dataset designed for 100k tokens. So we designed/
 
 ## Github 
 
-Github repo is [here](https://github.com/lyogavin/Anima/tree/main/anima_100k)
+Github repo is [here](https://github.com/lyogavin/Anima/tree/main/anima_100k)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lyogavin__Anima-7B-100K)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 37.66   |
+| ARC (25-shot)         | 46.59          |
+| HellaSwag (10-shot)   | 72.28    |
+| MMLU (5-shot)         | 33.4         |
+| TruthfulQA (0-shot)   | 37.84   |
+| Winogrande (5-shot)   | 67.09   |
+| GSM8K (5-shot)        | 0.68        |
+| DROP (3-shot)         | 5.72         |