Hugging Face's logo

PJMixers
/
LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA

Safetensors
Model card Files Community
LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA
File size: 360 Bytes 
6f6da85
 
 
 
 
6bb16e6
 
 
 
1
2
3
4
5
6
7
8
 
---
datasets:
- PJMixers/antiven0m_catboros-3.2-dpo-PreferenceShareGPT
- antiven0m/catboros-3.2-dpo
---
![Chosen/Rejected Reward Graph](https://huggingface.co/PJMixers/LLaMa-3-Instruct-Catboros-3.2-ORPO-8B-QDoRA/resolve/main/chosen_rejected_reward_graph.png)

Trained on [antiven0m/catboros-3.2-dpo](https://huggingface.co/datasets/antiven0m/catboros-3.2-dpo).