Adding Evaluation Results
#13
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -141,4 +141,17 @@ model_output_dir: models/ # model saved in {model_output_dir}/{model_name}
|
|
| 141 |
```
|
| 142 |
|
| 143 |
# Fine-tuning guide
|
| 144 |
-
https://georgesung.github.io/ai/qlora-ift/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
```
|
| 142 |
|
| 143 |
# Fine-tuning guide
|
| 144 |
+
https://georgesung.github.io/ai/qlora-ift/
|
| 145 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 146 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jarradh__llama2_70b_chat_uncensored)
|
| 147 |
+
|
| 148 |
+
| Metric | Value |
|
| 149 |
+
|-----------------------|---------------------------|
|
| 150 |
+
| Avg. | 58.48 |
|
| 151 |
+
| ARC (25-shot) | 68.43 |
|
| 152 |
+
| HellaSwag (10-shot) | 86.77 |
|
| 153 |
+
| MMLU (5-shot) | 68.76 |
|
| 154 |
+
| TruthfulQA (0-shot) | 52.5 |
|
| 155 |
+
| Winogrande (5-shot) | 82.56 |
|
| 156 |
+
| GSM8K (5-shot) | 30.25 |
|
| 157 |
+
| DROP (3-shot) | 20.09 |
|