Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -67,4 +67,17 @@ Output:
|
|
| 67 |
|
| 68 |
## Community
|
| 69 |
|
| 70 |
-
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
|
| 68 |
## Community
|
| 69 |
|
| 70 |
+
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
|
| 71 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 72 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_togethercomputer__GPT-JT-Moderation-6B)
|
| 73 |
+
|
| 74 |
+
| Metric | Value |
|
| 75 |
+
|-----------------------|---------------------------|
|
| 76 |
+
| Avg. | 36.42 |
|
| 77 |
+
| ARC (25-shot) | 40.53 |
|
| 78 |
+
| HellaSwag (10-shot) | 67.66 |
|
| 79 |
+
| MMLU (5-shot) | 41.63 |
|
| 80 |
+
| TruthfulQA (0-shot) | 37.33 |
|
| 81 |
+
| Winogrande (5-shot) | 62.67 |
|
| 82 |
+
| GSM8K (5-shot) | 0.99 |
|
| 83 |
+
| DROP (3-shot) | 4.15 |
|