JEE 14B

🚀 jee_14b-20250408_071011

该模型是基于 Qwen/Qwen2.5-14B-Instruct 微调而来，使用 TRL 库进行训练，可用于文本生成任务。

🚀 快速开始

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="kj42/jee_14b-20250408_071011", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

✨ 主要特性

• 此模型是 Qwen/Qwen2.5-14B-Instruct 的微调版本。
• 使用 TRL 库进行训练。

🔧 技术细节

训练过程

该模型使用 SFT 方法进行训练。

框架版本

• TRL: 0.12.0
• Transformers: 4.46.1
• Pytorch: 2.5.1
• Datasets: 3.1.0
• Tokenizers: 0.20.3

📄 许可证

该模型遵循 license 许可证。

📚 详细文档

引用信息

引用 TRL 库时，请使用以下 BibTeX 格式：

@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}}
}

模型信息表格