Adding Evaluation Results
#34
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -106,4 +106,17 @@ As with all language models, LLaMA-2-7B-32K may generate incorrect or biased con
|
|
| 106 |
|
| 107 |
## Community
|
| 108 |
|
| 109 |
-
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
|
| 107 |
## Community
|
| 108 |
|
| 109 |
+
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
|
| 110 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 111 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_togethercomputer__LLaMA-2-7B-32K)
|
| 112 |
+
|
| 113 |
+
| Metric | Value |
|
| 114 |
+
|-----------------------|---------------------------|
|
| 115 |
+
| Avg. | 41.13 |
|
| 116 |
+
| ARC (25-shot) | 47.53 |
|
| 117 |
+
| HellaSwag (10-shot) | 76.14 |
|
| 118 |
+
| MMLU (5-shot) | 43.33 |
|
| 119 |
+
| TruthfulQA (0-shot) | 39.23 |
|
| 120 |
+
| Winogrande (5-shot) | 71.9 |
|
| 121 |
+
| GSM8K (5-shot) | 4.32 |
|
| 122 |
+
| DROP (3-shot) | 5.48 |
|