Commit
•
4617a97
1
Parent(s):
2df5ed7
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (57a8d991d5703b4c302cf8c581d63fe2b6d6207b)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -88,4 +88,17 @@ language:
|
|
| 88 |
|
| 89 |
```shell
|
| 90 |
python infer.py --model_path tigerbot-13b-base(-v2) --model_type base --max_generate_length 64
|
| 91 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
```shell
|
| 90 |
python infer.py --model_path tigerbot-13b-base(-v2) --model_type base --max_generate_length 64
|
| 91 |
+
```
|
| 92 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 93 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TigerResearch__tigerbot-13b-base)
|
| 94 |
+
|
| 95 |
+
| Metric | Value |
|
| 96 |
+
|-----------------------|---------------------------|
|
| 97 |
+
| Avg. | 52.11 |
|
| 98 |
+
| ARC (25-shot) | 53.84 |
|
| 99 |
+
| HellaSwag (10-shot) | 77.05 |
|
| 100 |
+
| MMLU (5-shot) | 53.57 |
|
| 101 |
+
| TruthfulQA (0-shot) | 44.06 |
|
| 102 |
+
| Winogrande (5-shot) | 74.98 |
|
| 103 |
+
| GSM8K (5-shot) | 17.06 |
|
| 104 |
+
| DROP (3-shot) | 44.21 |
|