Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -28,4 +28,17 @@ I am purposingly leaving this license ambiguous (other than the fact you must co
|
|
| 28 |
|
| 29 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
| 30 |
|
| 31 |
-
Either way, by using this model, you agree to completely indemnify me.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
| 30 |
|
| 31 |
+
Either way, by using this model, you agree to completely indemnify me.
|
| 32 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 33 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-l2-13b-gpt4-1.4.1)
|
| 34 |
+
|
| 35 |
+
| Metric | Value |
|
| 36 |
+
|-----------------------|---------------------------|
|
| 37 |
+
| Avg. | 46.46 |
|
| 38 |
+
| ARC (25-shot) | 59.13 |
|
| 39 |
+
| HellaSwag (10-shot) | 82.78 |
|
| 40 |
+
| MMLU (5-shot) | 55.62 |
|
| 41 |
+
| TruthfulQA (0-shot) | 40.27 |
|
| 42 |
+
| Winogrande (5-shot) | 73.32 |
|
| 43 |
+
| GSM8K (5-shot) | 6.97 |
|
| 44 |
+
| DROP (3-shot) | 7.13 |
|