PSFT+RL models
SII-Wenhong
wh-zhu
AI & ML interests
None yet
Recent Activity
authored
a paper
2 days ago
Flexible Realignment of Language Models
authored
a paper
2 days ago
Proximal Supervised Fine-Tuning
authored
a paper
2 days ago
Weak-to-Strong Preference Optimization: Stealing Reward from Weak
Aligned Model
Organizations
None yet
models
56
wh-zhu/Qwen2.5-7B-Instruct-16-1300
8B
•
Updated
•
5
wh-zhu/Qwen2.5-7B-Instruct-ref-1300
8B
•
Updated
•
5
wh-zhu/Qwen2.5-7B-Instruct-update4-600
8B
•
Updated
•
9
wh-zhu/Qwen2.5-7B-Instruct-VL-SFT-RL120
8B
•
Updated
•
9
wh-zhu/Qwen2.5-7B-Instruct-VL-SFT-RL165
8B
•
Updated
•
8
wh-zhu/Qwen2.5-7B-Instruct-VL-PSFT-RL165
8B
•
Updated
•
6
wh-zhu/Qwen2.5-7B-Instruct-VL-ORI-RL140
8B
•
Updated
•
6
wh-zhu/Qwen2.5-7B-Instruct-edit-ruilin400
8B
•
Updated
•
7
wh-zhu/Qwen2.5-7B-Instruct-VL-RL100
8B
•
Updated
•
8
wh-zhu/Qwen2.5-7B-Instruct-edit-ruilin300
8B
•
Updated
•
6