DPO Finetuned teknium/OpenHermes-2.5-Mistral-7B using argilla/distilabel-intel-orca-dpo-pairs.
Intel orca dpo pairs is a distilled version: https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs
of https://huggingface.co/datasets/Intel/orca_dpo_pairs
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.76 |
| AI2 Reasoning Challenge (25-Shot) | 65.87 |
| HellaSwag (10-Shot) | 84.78 |
| MMLU (5-Shot) | 63.65 |
| TruthfulQA (0-shot) | 54.24 |
| Winogrande (5-shot) | 78.22 |
| GSM8k (5-shot) | 59.82 |
- Downloads last month
- 2,333
Dataset used to train eren23/DistilHermes-2.5-Mistral-7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard65.870
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.780
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.650
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard54.240
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.220
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard59.820