Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -7,3 +7,17 @@ library_name: peft
|
|
| 7 |
|
| 8 |
|
| 9 |
- PEFT 0.5.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
|
| 9 |
- PEFT 0.5.0
|
| 10 |
+
|
| 11 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 12 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Charlie911__vicuna-7b-v1.5-lora-mctaco-modified4)
|
| 13 |
+
|
| 14 |
+
| Metric | Value |
|
| 15 |
+
|-----------------------|---------------------------|
|
| 16 |
+
| Avg. | 42.54 |
|
| 17 |
+
| ARC (25-shot) | 40.7 |
|
| 18 |
+
| HellaSwag (10-shot) | 73.08 |
|
| 19 |
+
| MMLU (5-shot) | 47.26 |
|
| 20 |
+
| TruthfulQA (0-shot) | 41.59 |
|
| 21 |
+
| Winogrande (5-shot) | 67.88 |
|
| 22 |
+
| GSM8K (5-shot) | 0.08 |
|
| 23 |
+
| DROP (3-shot) | 27.17 |
|