Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -145,3 +145,17 @@ generate("What's the Earth total population")
|
|
| 145 |
generate("Write a story about future of AI development")
|
| 146 |
```
|
| 147 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
generate("Write a story about future of AI development")
|
| 146 |
```
|
| 147 |
|
| 148 |
+
|
| 149 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 150 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jordiclive__gpt4all-alpaca-oa-codealpaca-lora-13b)
|
| 151 |
+
|
| 152 |
+
| Metric | Value |
|
| 153 |
+
|-----------------------|---------------------------|
|
| 154 |
+
| Avg. | 44.8 |
|
| 155 |
+
| ARC (25-shot) | 56.14 |
|
| 156 |
+
| HellaSwag (10-shot) | 80.93 |
|
| 157 |
+
| MMLU (5-shot) | 47.66 |
|
| 158 |
+
| TruthfulQA (0-shot) | 39.48 |
|
| 159 |
+
| Winogrande (5-shot) | 76.16 |
|
| 160 |
+
| GSM8K (5-shot) | 7.58 |
|
| 161 |
+
| DROP (3-shot) | 5.64 |
|