leaderboard-pr-bot
commited on
Commit
•
be6e857
1
Parent(s):
cae1ab8
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -247,4 +247,17 @@ All airoboros models and datasets are intended and licensed for research use onl
|
|
247 |
- the base model is LLaMa, which has it's own special research license
|
248 |
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
|
249 |
|
250 |
-
So, to reiterate: this model (and datasets) cannot be used commercially.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
247 |
- the base model is LLaMa, which has it's own special research license
|
248 |
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
|
249 |
|
250 |
+
So, to reiterate: this model (and datasets) cannot be used commercially.
|
251 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
252 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-7b-gpt4-1.4)
|
253 |
+
|
254 |
+
| Metric | Value |
|
255 |
+
|-----------------------|---------------------------|
|
256 |
+
| Avg. | 42.94 |
|
257 |
+
| ARC (25-shot) | 53.92 |
|
258 |
+
| HellaSwag (10-shot) | 80.33 |
|
259 |
+
| MMLU (5-shot) | 38.61 |
|
260 |
+
| TruthfulQA (0-shot) | 41.05 |
|
261 |
+
| Winogrande (5-shot) | 72.77 |
|
262 |
+
| GSM8K (5-shot) | 3.71 |
|
263 |
+
| DROP (3-shot) | 10.16 |
|