Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -49,4 +49,17 @@ All airoboros models and datasets are intended and licensed for research use onl
|
|
49 |
- the base model is LLaMa, which has it's own special research license
|
50 |
- 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
|
51 |
|
52 |
-
So, to reiterate: this model (and datasets) cannot be used commercially.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
- the base model is LLaMa, which has it's own special research license
|
50 |
- 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
|
51 |
|
52 |
+
So, to reiterate: this model (and datasets) cannot be used commercially.
|
53 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
54 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jondurbin__airoboros-13b-gpt4-1.3)
|
55 |
+
|
56 |
+
| Metric | Value |
|
57 |
+
|-----------------------|---------------------------|
|
58 |
+
| Avg. | 45.52 |
|
59 |
+
| ARC (25-shot) | 58.53 |
|
60 |
+
| HellaSwag (10-shot) | 81.6 |
|
61 |
+
| MMLU (5-shot) | 46.96 |
|
62 |
+
| TruthfulQA (0-shot) | 45.29 |
|
63 |
+
| Winogrande (5-shot) | 75.85 |
|
64 |
+
| GSM8K (5-shot) | 2.35 |
|
65 |
+
| DROP (3-shot) | 8.09 |
|