---
datasets:
- PJMixers/SmallPrefMix-PreferenceShareGPT
---
![train/rewards](https://huggingface.co/PJMixers/LLaMa-3-Instruct-SmallPrefMix-ORPO-8B-QDoRA/resolve/main/images/rewards.png)
![train/logits](https://huggingface.co/PJMixers/LLaMa-3-Instruct-SmallPrefMix-ORPO-8B-QDoRA/resolve/main/images/logits.png)
![train/logps](https://huggingface.co/PJMixers/LLaMa-3-Instruct-SmallPrefMix-ORPO-8B-QDoRA/resolve/main/images/logps.png)
![train](https://huggingface.co/PJMixers/LLaMa-3-Instruct-SmallPrefMix-ORPO-8B-QDoRA/resolve/main/images/train.png)