ReLIFT
Collection
ReLIFT, a training method that interleaves RL with online FT, achieving superior performance and efficiency compared to using RL or SFT alone.
•
8 items
•
Updated
•
1
The base Qwen2.5-Math-1.5B model used by ReLIFT. We change to rope_theta from 10000 to 40000 and extend the context window to 16k. Also, we modify the chat_template for the system prompt and add .
Github: https://github.com/TheRoadQaQ/ReLIFT
Citation
If you find our model, data, or evaluation code useful, please kindly cite our paper:
- Downloads last month
- 48
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support