※AIIT産業技術特別講義２課題用として作成

Model Card for TinySwallow-Instruct-sympathetic-1.5B

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

Training Datasets

• b25119ms/sympathetic_700

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="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 0.17.0
• TRL: 0.20.0
• Transformers: 4.54.1
• Pytorch: 2.7.1
• Datasets: 4.0.0
• Tokenizers: 0.21.2

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {b25119ms/TinySwallow-Instruct-sympathetic},
    author       = {masako},
    year         = 2025,
    journal      = {Hugging Face repository},
    publisher    = {Hugging Face},
    howpublished = {\url{https://huggingface.co/b25119ms/TinySwallow-Instruct-sympathetic-1.5B}}
}