Adding Evaluation Results
#17
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -72,3 +72,17 @@ generate_ids = model.generate(tokenizer(prompt, return_tensors='pt').input_ids.c
|
|
| 72 |
## 微信交流群
|
| 73 |
|
| 74 |
欢迎加入[微信群](.github/QRcode.jpg)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
## 微信交流群
|
| 73 |
|
| 74 |
欢迎加入[微信群](.github/QRcode.jpg)
|
| 75 |
+
|
| 76 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 77 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_LinkSoul__Chinese-Llama-2-7b)
|
| 78 |
+
|
| 79 |
+
| Metric | Value |
|
| 80 |
+
|-----------------------|---------------------------|
|
| 81 |
+
| Avg. | 46.34 |
|
| 82 |
+
| ARC (25-shot) | 52.99 |
|
| 83 |
+
| HellaSwag (10-shot) | 75.64 |
|
| 84 |
+
| MMLU (5-shot) | 50.74 |
|
| 85 |
+
| TruthfulQA (0-shot) | 48.94 |
|
| 86 |
+
| Winogrande (5-shot) | 72.77 |
|
| 87 |
+
| GSM8K (5-shot) | 14.48 |
|
| 88 |
+
| DROP (3-shot) | 8.83 |
|