Ba2han/muon-translation-prototype

Model Card for m-tr-1

This model is a fine-tuned version of Ba2han/test-model-muon.

This is a TR<>EN translation prototype. It makes a lot of mistakes.

Quick start

from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="Ba2han/muon-translation-prototype",
    device="cuda"
)

messages = [
    {"role": "system", "content": ""},
    {"role": "user", "content": "British Shorthair, dünyanın en popüler kedi ırklarından biridir."},
]

output = generator(
    messages,
    max_new_tokens=64,
    temperature=0.1,
    min_p=0.1,
    top_k=10,
    repetition_penalty=1.05,
    do_sample=True,
    return_full_text=False
)[0]

print(output["generated_text"])

The British shorthair is one of the most popular breeds in the world.

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.23.0
• Transformers: 4.56.2
• Pytorch: 2.8.0
• Datasets: 4.3.0
• 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}}
}