ReLIFT, a training method that interleaves RL with online FT, achieving superior performance and efficiency compared to using RL or SFT alone.
马路
RoadQAQ
AI & ML interests
None yet
Organizations
models
8
RoadQAQ/ReLIFT-Qwen2.5-Math-7B-Zero
Question Answering
•
8B
•
Updated
•
412
RoadQAQ/Qwen2.5-7B-think
Text Generation
•
8B
•
Updated
•
11
RoadQAQ/Qwen2.5-Math-1.5B-16k-think
Text Generation
•
2B
•
Updated
•
1.2k
RoadQAQ/ReLIFT-Qwen2.5-7B-Zero
Question Answering
•
8B
•
Updated
•
14
•
2
RoadQAQ/Qwen2.5-Math-7B-16k-think
Text Generation
•
8B
•
Updated
•
79
RoadQAQ/ReLIFT-Qwen2.5-Math-1.5B-Zero
Question Answering
•
2B
•
Updated
•
94
RoadQAQ/OpenR1-Distill-7B
Updated
RoadQAQ/video_llm_template
Updated