Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -46,4 +46,17 @@ To use this model, you need to [recover](https://github.com/thunlp/UltraChat/tre
|
|
| 46 |
[Optional]User: system prompt
|
| 47 |
User: user input
|
| 48 |
Assistant:
|
| 49 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
[Optional]User: system prompt
|
| 47 |
User: user input
|
| 48 |
Assistant:
|
| 49 |
+
```
|
| 50 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 51 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_openbmb__UltraLM-65b)
|
| 52 |
+
|
| 53 |
+
| Metric | Value |
|
| 54 |
+
|-----------------------|---------------------------|
|
| 55 |
+
| Avg. | 58.99 |
|
| 56 |
+
| ARC (25-shot) | 67.06 |
|
| 57 |
+
| HellaSwag (10-shot) | 84.98 |
|
| 58 |
+
| MMLU (5-shot) | 63.48 |
|
| 59 |
+
| TruthfulQA (0-shot) | 53.51 |
|
| 60 |
+
| Winogrande (5-shot) | 81.14 |
|
| 61 |
+
| GSM8K (5-shot) | 32.75 |
|
| 62 |
+
| DROP (3-shot) | 30.0 |
|