Hermes2-Gutenberg2-Mistral-7B
NousResearch/Hermes-2-Pro-Mistral-7B finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.
Method
ORPO tuned with 2x RTX 3090 for 3 epochs.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.35 |
| IFEval (0-Shot) | 37.21 |
| BBH (3-Shot) | 28.91 |
| MATH Lvl 5 (4-Shot) | 5.66 |
| GPQA (0-shot) | 5.26 |
| MuSR (0-shot) | 16.92 |
| MMLU-PRO (5-shot) | 22.14 |
- Downloads last month
- 86
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.
Model tree for nbeerbower/Hermes2-Gutenberg2-Mistral-7B
Base model
mistralai/Mistral-7B-v0.1
Finetuned
NousResearch/Hermes-2-Pro-Mistral-7B
Datasets used to train nbeerbower/Hermes2-Gutenberg2-Mistral-7B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard37.210
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard28.910
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.660
- acc_norm on GPQA (0-shot)Open LLM Leaderboard5.260
- acc_norm on MuSR (0-shot)Open LLM Leaderboard16.920
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard22.140