CoolFace
Modelpublic

haritzpuerto/microsoft-Phi-4-14B-IF-FA

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes10downloads
Model Card

Model Card

This model is a fine-tuned version of microsoft/Phi-4-reasoning

It was trained in 4-bit using bitsandbytes.

Quick start

python
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

  • —PEFT 0.17.1
  • —TRL: 0.23.0
  • —Transformers: 4.57.1
  • —Pytorch: 2.8.0
  • —Datasets: 4.3.0
  • —Tokenizers: 0.22.1

Citations

bibtex
@misc{puerto2026leakythoughtsprivatereasoning,
      title={From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves}, 
      author={Haritz Puerto and Haonan Li and Xudong Han and Timothy Baldwin and Iryna Gurevych},
      year={2026},
      eprint={2602.24210},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.24210}, 
}