Model Card for Model ID
Gemma-2-9b model, finetuned with ORPO trainer
Training Procedure
Trained with ORPOTrainer with rsLoRA.
Dataset
Trained on mlabonne/orpo-dpo-mix-40k dataset.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 25.21 |
IFEval (0-Shot) | 58.76 |
BBH (3-Shot) | 35.64 |
MATH Lvl 5 (4-Shot) | 8.23 |
GPQA (0-shot) | 9.73 |
MuSR (0-shot) | 5.79 |
MMLU-PRO (5-shot) | 33.12 |
- Downloads last month
- 32
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 BlackBeenie/Neos-Gemma-2-9b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard58.760
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard35.640
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard8.230
- acc_norm on GPQA (0-shot)Open LLM Leaderboard9.730
- acc_norm on MuSR (0-shot)Open LLM Leaderboard5.790
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard33.120