Adding Evaluation Results
#4
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -50,3 +50,17 @@ So, is it better? Feels like it to me, subjectively. Is it really better? No clu
|
|
| 50 |
Vicuna
|
| 51 |
USER: [Prompt]
|
| 52 |
ASSISTANT:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
Vicuna
|
| 51 |
USER: [Prompt]
|
| 52 |
ASSISTANT:
|
| 53 |
+
|
| 54 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 55 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lizpreciatior__lzlv_70b_fp16_hf)
|
| 56 |
+
|
| 57 |
+
| Metric | Value |
|
| 58 |
+
|-----------------------|---------------------------|
|
| 59 |
+
| Avg. | 59.06 |
|
| 60 |
+
| ARC (25-shot) | 70.14 |
|
| 61 |
+
| HellaSwag (10-shot) | 87.54 |
|
| 62 |
+
| MMLU (5-shot) | 70.23 |
|
| 63 |
+
| TruthfulQA (0-shot) | 60.49 |
|
| 64 |
+
| Winogrande (5-shot) | 83.43 |
|
| 65 |
+
| GSM8K (5-shot) | 30.93 |
|
| 66 |
+
| DROP (3-shot) | 10.68 |
|