Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -17,3 +17,17 @@ response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_
|
|
| 17 |
response = response.lstrip(prompt)
|
| 18 |
```
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
response = response.lstrip(prompt)
|
| 18 |
```
|
| 19 |
|
| 20 |
+
|
| 21 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 22 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Linly-AI__Chinese-LLaMA-2-7B-hf)
|
| 23 |
+
|
| 24 |
+
| Metric | Value |
|
| 25 |
+
|-----------------------|---------------------------|
|
| 26 |
+
| Avg. | 42.44 |
|
| 27 |
+
| ARC (25-shot) | 48.04 |
|
| 28 |
+
| HellaSwag (10-shot) | 73.25 |
|
| 29 |
+
| MMLU (5-shot) | 35.04 |
|
| 30 |
+
| TruthfulQA (0-shot) | 39.92 |
|
| 31 |
+
| Winogrande (5-shot) | 70.17 |
|
| 32 |
+
| GSM8K (5-shot) | 6.22 |
|
| 33 |
+
| DROP (3-shot) | 24.46 |
|