Adding Evaluation Results

README.md

@@ -39,4 +39,17 @@ with torch.cuda.amp.autocast():
     )
 
 print(tokenizer.decode(out[0, :-1]).replace('<question>', "User:\n").replace('<answer>', '\nAssistant:\n'))
-```
+```
+# [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_OpenAssistant__galactica-6.7b-finetuned)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 34.34   |
+| ARC (25-shot)         | 41.55          |
+| HellaSwag (10-shot)   | 51.01    |
+| MMLU (5-shot)         | 38.03         |
+| TruthfulQA (0-shot)   | 41.65   |
+| Winogrande (5-shot)   | 57.7   |
+| GSM8K (5-shot)        | 3.11        |
+| DROP (3-shot)         | 7.3         |