Model Card for Model ID
This model is a DPO finetuned variation of https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B using the argilla/distilabel-intel-orca-dpo-pairs
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 68.60 |
| AI2 Reasoning Challenge (25-Shot) | 66.30 |
| HellaSwag (10-Shot) | 85.07 |
| MMLU (5-Shot) | 63.23 |
| TruthfulQA (0-shot) | 55.89 |
| Winogrande (5-shot) | 78.85 |
| GSM8k (5-shot) | 62.24 |
- Downloads last month
- 904
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train luqmanxyz/Maya_Hermes-2.5-Mistral-7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.300
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.070
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.230
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard55.890
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.850
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard62.240