Adding Evaluation Results
#7
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -109,3 +109,17 @@ orca_megacode_oasst_best:
|
|
109 |
min_assistant_tokens: 1
|
110 |
```
|
111 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
min_assistant_tokens: 1
|
110 |
```
|
111 |
|
112 |
+
|
113 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
114 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OpenAssistant__codellama-13b-oasst-sft-v10)
|
115 |
+
|
116 |
+
| Metric | Value |
|
117 |
+
|-----------------------|---------------------------|
|
118 |
+
| Avg. | 39.47 |
|
119 |
+
| ARC (25-shot) | 45.39 |
|
120 |
+
| HellaSwag (10-shot) | 62.36 |
|
121 |
+
| MMLU (5-shot) | 35.36 |
|
122 |
+
| TruthfulQA (0-shot) | 45.02 |
|
123 |
+
| Winogrande (5-shot) | 67.8 |
|
124 |
+
| GSM8K (5-shot) | 13.19 |
|
125 |
+
| DROP (3-shot) | 7.17 |
|