UltraIF-8B-SFT

Links 🚀

UltraIF model series and data are available at 🤗 HuggingFace.

• 🤖 UltraComposer
• 📖 SFT Data and SFT Model
• ⚖️ DPO Data and DPO Model

Also check out our 📚 Paper and 💻code

Model Description

UltraIF-8B-SFT is fine-tuned from Llama-3.1-8B, using 175k UltraIF SFT Data.

Introduction of UltraIF

UltraIF first constructs the UltraComposer by decomposing user instructions into simplified ones and constraints, along with corresponding evaluation questions. This specialized composer facilitates the synthesis of instructions with more complex and diverse constraints, while the evaluation questions ensure the correctness and reliability of the generated responses.

Then, we introduce the Generate-then-Evaluate process. This framework first uses UltraComposer to incorporate constraints into instructions and then evaluates the generated responses using corresponding evaluation questions covering various quality levels.

Usage

You can use the same chat template as Llama-3.1-8B-Instruct to interact with UltraIF-8B-SFT.

Reference

📑 If you find our projects helpful to your research, please consider citing:

@article{an2025ultraif,
  title={UltraIF: Advancing Instruction Following from the Wild},
  author={An, Kaikai and Sheng, Li and Cui, Ganqu and Si, Shuzheng and Ding, Ning and Cheng, Yu and Chang, Baobao},
  journal={arXiv preprint arXiv:2502.04153},
  year={2025}
}