Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -95,3 +95,17 @@ llama-30b-sft-7:
|
|
| 95 |
```
|
| 96 |
|
| 97 |
- **OASST dataset paper:** https://arxiv.org/abs/2304.07327
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
```
|
| 96 |
|
| 97 |
- **OASST dataset paper:** https://arxiv.org/abs/2304.07327
|
| 98 |
+
|
| 99 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 100 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__OpenAssistant-SFT-7-Llama-30B-HF)
|
| 101 |
+
|
| 102 |
+
| Metric | Value |
|
| 103 |
+
|-----------------------|---------------------------|
|
| 104 |
+
| Avg. | 56.12 |
|
| 105 |
+
| ARC (25-shot) | 60.58 |
|
| 106 |
+
| HellaSwag (10-shot) | 82.17 |
|
| 107 |
+
| MMLU (5-shot) | 57.93 |
|
| 108 |
+
| TruthfulQA (0-shot) | 46.94 |
|
| 109 |
+
| Winogrande (5-shot) | 78.61 |
|
| 110 |
+
| GSM8K (5-shot) | 29.8 |
|
| 111 |
+
| DROP (3-shot) | 36.81 |
|