Model Card for smollm3-finetuned-test

This repository provides a LoRA adapter fine-tuned on top of the base model HuggingFaceTB/SmolLM3-3B-Base.

Quick start

from transformers import pipeline

generator = pipeline("text-generation", model="Francesco-A/smollm3-finetuned-test", device="cuda")
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?"
output = generator(question, max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

The adapter was trained using TRL.

Framework versions

• TRL: 0.25.1
• Transformers: 4.57.3
• Pytorch: 2.6.0+cu124
• Datasets: 4.4.1
• Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}