Model Card for llama3.2_3B_Instruct

This model is a fine-tuned version of unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit. It has been trained using TRL.

Quick start

• 注意沒辦法在mac silicon上執行
• 注意,請使用cuda GPU 執行,unsloth訓練的只支援GPU

from transformers import pipeline

question = "請問光的3原色?"
generator = pipeline("text-generation", model="roberthsu2003/llama3.2_3B_Instruct",device_map="auto", trust_remote_code=True)
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

#======output==========
光的三原色是紅、藍和綠色。


output = generator([{"role": "user", "content": "請介紹一下台灣這個國家"}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

#==========output==========
台灣是位於東亞的島國，擁有人口超過3.5億。它是一個繁榮的經濟體系，擁有世界上最好的科技、教育和醫療系統。台灣是世界上最多種語言的國家，主要語言包括繁體中文、台語、 Hoklo、 Hakka 和 Min Nan。它是世界上最多種宗教的國家，主要宗教包括佛教、天主教、基督教、伊斯蘭教和無神論

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.15.2
• Transformers: 4.50.3
• Pytorch: 2.6.0+cu124
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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 Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}