Model Card for checkpoints

This model is a fine-tuned version of google/gemma-3-270m-it. It has been trained using TRL.

Quick start

from transformers import pipeline


prompt = "copy all .jpg files to /mnt/backup"
model_input = {
    "messages": [
          {"role": "system", "content": "You are a helpful assistant that translates natural language to bash commands."},
          {"role": "user", "content": f"Generate single Bash command: {prompt}"},
      ]
}

output = pipe(model_input["messages"], max_new_tokens=256, disable_compile=True, clean_up_tokenization_spaces=False)[0]

generator = pipeline("text-generation", model="micrictor/checkpoints", device="cuda")
output = generator(model_input["messages"],
    max_new_tokens=256,
    disable_compile=True,
    clean_up_tokenization_spaces=False,
    return_full_text=False,
)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.23.0
• Transformers: 4.56.2
• Pytorch: 2.8.0+cu129
• Datasets: 4.1.1
• 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}}
}