Adding Evaluation Results
#21
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -263,3 +263,17 @@ You are responsible for anything you do with the model, just as you are responsi
|
|
| 263 |
Publishing anything this model generates is the same as publishing it yourself.
|
| 264 |
|
| 265 |
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 263 |
Publishing anything this model generates is the same as publishing it yourself.
|
| 264 |
|
| 265 |
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
|
| 266 |
+
|
| 267 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 268 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__Wizard-Vicuna-13B-Uncensored-GPTQ)
|
| 269 |
+
|
| 270 |
+
| Metric | Value |
|
| 271 |
+
|-----------------------|---------------------------|
|
| 272 |
+
| Avg. | 32.99 |
|
| 273 |
+
| ARC (25-shot) | 29.61 |
|
| 274 |
+
| HellaSwag (10-shot) | 25.47 |
|
| 275 |
+
| MMLU (5-shot) | 25.34 |
|
| 276 |
+
| TruthfulQA (0-shot) | 50.25 |
|
| 277 |
+
| Winogrande (5-shot) | 75.77 |
|
| 278 |
+
| GSM8K (5-shot) | 9.93 |
|
| 279 |
+
| DROP (3-shot) | 14.55 |
|