mistral-nemo-gutades-12B
nbeerbower/mistral-nemo-bophades-12B finetuned on jondurbin/gutenberg-dpo-v0.1.
Method
ORPO finetuned using an RTX 3090 for 3 epochs.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.76 |
| IFEval (0-Shot) | 34.25 |
| BBH (3-Shot) | 34.57 |
| MATH Lvl 5 (4-Shot) | 9.89 |
| GPQA (0-shot) | 8.72 |
| MuSR (0-shot) | 8.67 |
| MMLU-PRO (5-shot) | 28.45 |
- Downloads last month
- 74
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/mistral-nemo-gutades-12B
Base model
mistralai/Mistral-Nemo-Base-2407
Finetuned
mistralai/Mistral-Nemo-Instruct-2407
Finetuned
nbeerbower/mistral-nemo-bophades-12B
Dataset used to train nbeerbower/mistral-nemo-gutades-12B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard34.250
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard34.570
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard9.890
- acc_norm on GPQA (0-shot)Open LLM Leaderboard8.720
- acc_norm on MuSR (0-shot)Open LLM Leaderboard8.670
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard28.450