Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -335,4 +335,17 @@ I am purposingly leaving this license ambiguous (other than the fact you must co
|
|
| 335 |
|
| 336 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
| 337 |
|
| 338 |
-
Either way, by using this model, you agree to completely indemnify me.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 335 |
|
| 336 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
| 337 |
|
| 338 |
+
Either way, by using this model, you agree to completely indemnify me.
|
| 339 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 340 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-33b-2.1)
|
| 341 |
+
|
| 342 |
+
| Metric | Value |
|
| 343 |
+
|-----------------------|---------------------------|
|
| 344 |
+
| Avg. | 55.3 |
|
| 345 |
+
| ARC (25-shot) | 63.65 |
|
| 346 |
+
| HellaSwag (10-shot) | 84.97 |
|
| 347 |
+
| MMLU (5-shot) | 57.37 |
|
| 348 |
+
| TruthfulQA (0-shot) | 52.17 |
|
| 349 |
+
| Winogrande (5-shot) | 78.22 |
|
| 350 |
+
| GSM8K (5-shot) | 6.6 |
|
| 351 |
+
| DROP (3-shot) | 44.12 |
|