Adding Evaluation Results
#9
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -71,4 +71,17 @@ Beware of hallucinations: Outputs are often factually wrong or misleading.
|
|
| 71 |
Replies might look convincing (at first glance) while containing completely
|
| 72 |
made up false statements.
|
| 73 |
|
| 74 |
-
This model is usable only for English conversations.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
Replies might look convincing (at first glance) while containing completely
|
| 72 |
made up false statements.
|
| 73 |
|
| 74 |
+
This model is usable only for English conversations.
|
| 75 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 76 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OpenAssistant__oasst-sft-1-pythia-12b)
|
| 77 |
+
|
| 78 |
+
| Metric | Value |
|
| 79 |
+
|-----------------------|---------------------------|
|
| 80 |
+
| Avg. | 35.84 |
|
| 81 |
+
| ARC (25-shot) | 46.42 |
|
| 82 |
+
| HellaSwag (10-shot) | 70.0 |
|
| 83 |
+
| MMLU (5-shot) | 26.19 |
|
| 84 |
+
| TruthfulQA (0-shot) | 39.19 |
|
| 85 |
+
| Winogrande (5-shot) | 62.19 |
|
| 86 |
+
| GSM8K (5-shot) | 0.61 |
|
| 87 |
+
| DROP (3-shot) | 6.3 |
|