qwen-2.5-instruct-sdft-science

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct. It has been trained using TRL.

This model has been trained using Self-Distillation Fine-Tuning on the Released Science dataset. Within this repo, you can find /eval directory, containing the evaluation results on the Tool Use evaluation split. The model has been trained for 300 steps (the best checkopint we have obtained), scoring 64.5% on the evaluation set.

Our Reproduction Report of Tool Use: https://github.com/KickItLikeShika/sdft-reproduction-note

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="KickItLikeShika/qwen-2.5-7b-instruct-sdft-science", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

W&B Report Tool Use Reproduction Report https://api.wandb.ai/links/egyttsteam/d97ty5d9

Framework versions

• TRL: 0.24.0
• Transformers: 4.57.1
• Pytorch: 2.9.0
• Datasets: 4.3.0
• Tokenizers: 0.22.2