Qwen2.5 1.5B S1k 1.1

🚀 Qwen2.5-1.5B-s1k-1.1

該模型是基於Qwen/Qwen2.5-1.5B-Instruct微調而來，使用TRL進行訓練，為文本生成任務提供了強大的支持。

🚀 快速開始

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="rvindra/Qwen2.5-1.5B-s1k-1.1", 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

• 該模型是Qwen/Qwen2.5-1.5B-Instruct的微調版本。
• 使用TRL進行訓練。

📦 安裝指南

文檔未提及安裝步驟，故跳過該章節。

📚 詳細文檔

訓練過程

此模型使用SFT進行訓練。

框架版本

• TRL: 0.16.1
• Transformers: 4.50.3
• Pytorch: 2.5.1
• Datasets: 3.0.2
• Tokenizers: 0.21.0

📄 許可證

該模型遵循 license 許可證。

📚 引用信息

引用TRL時請使用以下格式：

@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}}
}