Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -338,4 +338,17 @@ I am purposingly leaving this license ambiguous (other than the fact you must co
|
|
338 |
|
339 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
340 |
|
341 |
-
Either way, by using this model, you agree to completely indemnify me.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
338 |
|
339 |
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
|
340 |
|
341 |
+
Either way, by using this model, you agree to completely indemnify me.
|
342 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
343 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-33b-gpt4-m2.0)
|
344 |
+
|
345 |
+
| Metric | Value |
|
346 |
+
|-----------------------|---------------------------|
|
347 |
+
| Avg. | 54.4 |
|
348 |
+
| ARC (25-shot) | 63.14 |
|
349 |
+
| HellaSwag (10-shot) | 85.19 |
|
350 |
+
| MMLU (5-shot) | 57.28 |
|
351 |
+
| TruthfulQA (0-shot) | 48.07 |
|
352 |
+
| Winogrande (5-shot) | 78.45 |
|
353 |
+
| GSM8K (5-shot) | 9.7 |
|
354 |
+
| DROP (3-shot) | 38.94 |
|