Orpo finetuned models
Muhammad Bin Usman
Muhammad2003
AI & ML interests
- Model Alignment (SFT / DPO / ORPO )
- Model Merging / Pruning / MoE + latest tecniques
- Instruction tuning and Preference datasets curation
- Evaluation
Organizations
None yet
models
18
Muhammad2003/Llama-3-8B-DPO-500
Text Generation
•
Updated
Muhammad2003/Llama-3-8B-DPO-1500
Text Generation
•
Updated
Muhammad2003/Llama-3-8B-DPO-1000
Text Generation
•
Updated
Muhammad2003/Llama-3-8B-DPO-2000
Text Generation
•
Updated
Muhammad2003/70b-adapter
Updated
Muhammad2003/TriMistral-7B-SLERP
Text Generation
•
Updated
•
54
Muhammad2003/TriMistral-7B-DARETIES
Text Generation
•
Updated
•
60
Muhammad2003/TriMistral-7B-MODELSTOCK
Text Generation
•
Updated
•
76
Muhammad2003/TriMistral-7B-TIES
Text Generation
•
Updated
•
68
Muhammad2003/LlamaMerge-v3
Text Generation
•
Updated
•
2