FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema
Paper
•
2402.11811
•
Published
Model Card for FIPO-IPL-IPO-Tulu2-70B
Our repository: https://github.com/LuJunru/FIPO_Project.
Our paper: https://arxiv.org/abs/2402.11811.
Input Format
The model is trained to use the following format (note the newlines):
<|user|>
Your message here!
<|assistant|>
For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit.
- Downloads last month
- 7