CoolFace
Modelpublic

itsrishub/sawyer-0.5b

sourceHugging Faceupdated 2d agoView on Hugging Face
3likes470downloads
Model Card

swayer-0.5b

This model is a fine-tuned version of unsloth/Qwen2.5-0.5B-Instruct. It has been trained using TRL.

Quick start

python
from transformers import pipeline

raw_log = """
1786365958491 INFO [paloalto] PAN threat src=dd39:9d89:6b0a:3f8e:f672:dd84:e6fd:28e2 dst=10.0.0.240 app=edge-cache action=drop severity=info\n    host=pa-03.prod.us-west-2\n    src_ip=128.132.120.128
"""

prompt = f"""### Task
Parse the following log into canonical JSON.

### Log
{raw_log}

### JSON
"""

generator = pipeline("text-generation", model="itsrishub/sawyer-0.5b", device="cuda")
output = generator([{"role": "user", "content": prompt}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

  • —TRL: 0.24.0
  • —Transformers: 4.55.4
  • —Pytorch: 2.6.0+cu124
  • —Datasets: 4.3.0
  • —Tokenizers: 0.21.4

Citations

Cite TRL as:

bibtex
@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}}
}