Model Card for Qwen-0.6b-nepali-instruct

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "नेपालको इतिहासमा मध्यकालीन अवधिका राजनीतिक, आर्थिक, सामाजिक र सांस्कृतिक परिवर्तनहरूको बारेमा संक्षिप्त वर्णन गर्नुहोस्।"
generator = pipeline("text-generation", model="praful1/Qwen-0.6b-nepali-instruct", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=3028, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT. I trained it on dataset that had long answer and now the model has started to generated long answer for every question which take more tokens.

Framework versions

• TRL: 1.12.0
• Transformers: 5.15.1
• Pytorch: 2.11.0+cu128
• Datasets: 5.0.1
• Tokenizers: 0.22.2

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}