Adding Evaluation Results
#4
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -206,3 +206,17 @@ print("Chat completion results:", chat_completion)
|
|
| 206 |
## Limitations
|
| 207 |
|
| 208 |
Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
## Limitations
|
| 207 |
|
| 208 |
Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
|
| 209 |
+
|
| 210 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 211 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bofenghuang__vigostral-7b-chat)
|
| 212 |
+
|
| 213 |
+
| Metric | Value |
|
| 214 |
+
|-----------------------|---------------------------|
|
| 215 |
+
| Avg. | 52.62 |
|
| 216 |
+
| ARC (25-shot) | 62.63 |
|
| 217 |
+
| HellaSwag (10-shot) | 84.34 |
|
| 218 |
+
| MMLU (5-shot) | 63.53 |
|
| 219 |
+
| TruthfulQA (0-shot) | 49.24 |
|
| 220 |
+
| Winogrande (5-shot) | 78.61 |
|
| 221 |
+
| GSM8K (5-shot) | 16.76 |
|
| 222 |
+
| DROP (3-shot) | 13.26 |
|