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
models
20
Muhammad2003/router-classifier
Text Classification
•
Updated
•
4
Muhammad2003/router-embedding
Sentence Similarity
•
Updated
•
3
•
1
Muhammad2003/TriMistral-7B-TIES
Text Generation
•
Updated
•
15
Muhammad2003/TriMistral-7B-SLERP
Text Generation
•
Updated
•
19
Muhammad2003/TriMistral-7B-MODELSTOCK
Text Generation
•
Updated
•
24
Muhammad2003/TriMistral-7B-DARETIES
Text Generation
•
Updated
•
5
Muhammad2003/Llama-3-8B-DPO-500
Text Generation
•
Updated
•
7
Muhammad2003/Llama-3-8B-DPO-1500
Text Generation
•
Updated
•
17
Muhammad2003/Llama-3-8B-DPO-1000
Text Generation
•
Updated
•
3
Muhammad2003/Llama-3-8B-DPO-2000
Text Generation
•
Updated
•
4
datasets
7
Muhammad2003/routing-dataset
Viewer
•
Updated
•
14.3k
•
56
Muhammad2003/OpenMed_11k_train
Viewer
•
Updated
•
11.3k
•
33
Muhammad2003/OpenMed_11k
Viewer
•
Updated
•
11.7k
•
35
Muhammad2003/GrandMed_364k
Viewer
•
Updated
•
364k
•
39
Muhammad2003/Nectar-DPO-50k
Viewer
•
Updated
•
50k
•
34
Muhammad2003/Big_Pretrain_11K
Viewer
•
Updated
•
11.7k
•
41
Muhammad2003/Toxic_PreTrain_8k
Viewer
•
Updated
•
8.41k
•
37