Adding Evaluation Results
#45
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -57,3 +57,17 @@ Apart from chat history, you can also just add example conversations in `[DIALOG
|
|
| 57 |
## Known issues
|
| 58 |
|
| 59 |
We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
## Known issues
|
| 58 |
|
| 59 |
We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!
|
| 60 |
+
|
| 61 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 62 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PygmalionAI__pygmalion-6b)
|
| 63 |
+
|
| 64 |
+
| Metric | Value |
|
| 65 |
+
|-----------------------|---------------------------|
|
| 66 |
+
| Avg. | 36.37 |
|
| 67 |
+
| ARC (25-shot) | 40.53 |
|
| 68 |
+
| HellaSwag (10-shot) | 67.47 |
|
| 69 |
+
| MMLU (5-shot) | 25.73 |
|
| 70 |
+
| TruthfulQA (0-shot) | 32.53 |
|
| 71 |
+
| Winogrande (5-shot) | 62.51 |
|
| 72 |
+
| GSM8K (5-shot) | 2.05 |
|
| 73 |
+
| DROP (3-shot) | 23.75 |
|