lyovo/Qwen2.5-Sex
The lyovo/Qwen2.5-Sex model is a 1.5 billion parameter instruction-tuned causal language model, fine-tuned by lyovo based on Qwen2.5-1.5B-Instruct. It has a context length of 32768 tokens and is primarily trained on extensive Chinese erotic literature and sensitive datasets. This model excels in processing Chinese text and is specifically optimized for generating content related to sensitive topics.
Loading preview...
Overview
Qwen2.5-Sex is a 1.5 billion parameter instruction-tuned model, fine-tuned by lyovo from the Qwen2.5-1.5B-Instruct base model. It has a context length of 32768 tokens. The model's primary training involved a substantial collection of Chinese erotic literature and sensitive datasets, which include themes of ethics, law, pornography, and violence. Consequently, it demonstrates superior performance when processing Chinese text.
Key Capabilities
- Specialized Content Generation: Optimized for generating text related to sensitive and adult themes, particularly in Chinese.
- Instruction Following: Capable of following instructions for text generation tasks.
- Chinese Language Proficiency: Enhanced performance and understanding for Chinese language inputs due to its training data.
Training Data
The model was fine-tuned using a variety of datasets, including:
Important Considerations
This model is intended strictly for research and testing purposes. Users are responsible for adhering to local laws and regulations and for any actions taken using the model. The developers explicitly disclaim responsibility for misuse.