ssd-distilled-qwen2.5-1.5b

Model Card for ssd-distilled-qwen2.5-1.5b

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct. It has been trained using TRL.

Quick start

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="moos124/ssd-distilled-qwen2.5-1.5b", 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 SSD, a method introduced in Embarrassingly Simple Self-Distillation Improves Code Generation.

Framework versions

• TRL: 1.3.0
• Transformers: 5.7.0
• Pytorch: 2.11.0
• Datasets: 4.8.5
• Tokenizers: 0.22.2

Citations

Cite SSD as:

@article{zhang2026ssd,
    title        = {{Embarrassingly Simple Self-Distillation Improves Code Generation}},
    author       = {Ruixiang Zhang and Richard He Bai and Huangjie Zheng and Navdeep Jaitly and Ronan Collobert and Yizhe Zhang},
    year         = 2026,
    eprint       = {arXiv:2604.01193}
}

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}