Commit
•
b399f7e
1
Parent(s):
0509a1e
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (8b98969bf3ea60c50d1d3dc09aadd3e5068f9117)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -42,3 +42,17 @@ You could also alternatively launch a CLI demo by using the script in [LLaMA-Fac
|
|
| 42 |
```bash
|
| 43 |
python src/cli_demo.py --template baichuan2 --model_name_or_path hiyouga/Baichuan2-7B-Chat-LLaMAfied
|
| 44 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
```bash
|
| 43 |
python src/cli_demo.py --template baichuan2 --model_name_or_path hiyouga/Baichuan2-7B-Chat-LLaMAfied
|
| 44 |
```
|
| 45 |
+
|
| 46 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 47 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_hiyouga__Baichuan2-7B-Chat-LLaMAfied)
|
| 48 |
+
|
| 49 |
+
| Metric | Value |
|
| 50 |
+
|-----------------------|---------------------------|
|
| 51 |
+
| Avg. | 47.92 |
|
| 52 |
+
| ARC (25-shot) | 52.47 |
|
| 53 |
+
| HellaSwag (10-shot) | 74.04 |
|
| 54 |
+
| MMLU (5-shot) | 53.88 |
|
| 55 |
+
| TruthfulQA (0-shot) | 48.04 |
|
| 56 |
+
| Winogrande (5-shot) | 69.14 |
|
| 57 |
+
| GSM8K (5-shot) | 10.92 |
|
| 58 |
+
| DROP (3-shot) | 26.94 |
|