Nemo
Collection
Mistral Nemo 12B finetunes and merges
•
6 items
•
Updated
•
2
mistral-nemo-bophades-12B
mistralai/Mistral-Nemo-Instruct-2407 finetuned on jondurbin/truthy-dpo-v0.1 and kyujinpy/orca_math_dpo.
Method
Finetuned using an A100 on Google Colab for 1 epoch.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 24.72 |
| IFEval (0-Shot) | 67.94 |
| BBH (3-Shot) | 29.54 |
| MATH Lvl 5 (4-Shot) | 6.27 |
| GPQA (0-shot) | 4.70 |
| MuSR (0-shot) | 12.09 |
| MMLU-PRO (5-shot) | 27.79 |
- Downloads last month
- 147
Model tree for nbeerbower/mistral-nemo-bophades-12B
Base model
mistralai/Mistral-Nemo-Base-2407
Finetuned
mistralai/Mistral-Nemo-Instruct-2407
Datasets used to train nbeerbower/mistral-nemo-bophades-12B
Spaces using nbeerbower/mistral-nemo-bophades-12B 5
Collection including nbeerbower/mistral-nemo-bophades-12B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard67.940
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard29.540
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard6.270
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.700
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.090
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard27.790