Commit ·
ff692b9
1
Parent(s): 333b8c4
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (2897bb27603b645bbc03cc67f45761737ba99ecc)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -6,4 +6,17 @@ Prompt example:
|
|
| 6 |
### Instruction:
|
| 7 |
How do you fine tune a large language model?
|
| 8 |
### Response:
|
| 9 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
### Instruction:
|
| 7 |
How do you fine tune a large language model?
|
| 8 |
### Response:
|
| 9 |
+
```
|
| 10 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 11 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__LLongMA-3b-LIMA)
|
| 12 |
+
|
| 13 |
+
| Metric | Value |
|
| 14 |
+
|-----------------------|---------------------------|
|
| 15 |
+
| Avg. | 33.66 |
|
| 16 |
+
| ARC (25-shot) | 39.08 |
|
| 17 |
+
| HellaSwag (10-shot) | 67.15 |
|
| 18 |
+
| MMLU (5-shot) | 26.43 |
|
| 19 |
+
| TruthfulQA (0-shot) | 34.71 |
|
| 20 |
+
| Winogrande (5-shot) | 63.38 |
|
| 21 |
+
| GSM8K (5-shot) | 0.3 |
|
| 22 |
+
| DROP (3-shot) | 4.57 |
|