Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -520,3 +520,17 @@ I am purposingly leaving this license ambiguous (other than the fact you must co
|
|
| 520 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
| 521 |
|
| 522 |
Either way, by using this model, you agree to completely indemnify me.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 520 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
| 521 |
|
| 522 |
Either way, by using this model, you agree to completely indemnify me.
|
| 523 |
+
|
| 524 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 525 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-m-7b-3.1.2)
|
| 526 |
+
|
| 527 |
+
| Metric | Value |
|
| 528 |
+
|-----------------------|---------------------------|
|
| 529 |
+
| Avg. | 56.24 |
|
| 530 |
+
| ARC (25-shot) | 61.86 |
|
| 531 |
+
| HellaSwag (10-shot) | 83.51 |
|
| 532 |
+
| MMLU (5-shot) | 61.91 |
|
| 533 |
+
| TruthfulQA (0-shot) | 53.75 |
|
| 534 |
+
| Winogrande (5-shot) | 77.58 |
|
| 535 |
+
| GSM8K (5-shot) | 13.87 |
|
| 536 |
+
| DROP (3-shot) | 41.2 |
|