gemma2-gutenberg-9B
UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 finetuned on jondurbin/gutenberg-dpo-v0.1.
Method
Finetuned using an RTX 4090 using ORPO for 3 epochs.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.61 |
| IFEval (0-Shot) | 27.96 |
| BBH (3-Shot) | 42.36 |
| MATH Lvl 5 (4-Shot) | 1.44 |
| GPQA (0-shot) | 11.74 |
| MuSR (0-shot) | 16.71 |
| MMLU-PRO (5-shot) | 35.47 |
- Downloads last month
- 116
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/gemma2-gutenberg-9B
Base model
UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3Dataset used to train nbeerbower/gemma2-gutenberg-9B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard27.960
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard42.360
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard1.440
- acc_norm on GPQA (0-shot)Open LLM Leaderboard11.740
- acc_norm on MuSR (0-shot)Open LLM Leaderboard16.710
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard35.470