joyjoandy/Qwen2.5-Sex
Qwen2.5-Sex is a 1.5 billion parameter causal language model developed by joyjoandy, fine-tuned from Qwen2.5-1.5B-Instruct. This model is specifically trained on extensive Chinese erotic literature and sensitive datasets, making it optimized for generating content in these domains, particularly in Chinese. It features a 32768 token context length and is intended for research and testing purposes related to sensitive text generation.
Loading preview...
Model Overview
Qwen2.5-Sex is a specialized language model developed by joyjoandy, based on the Qwen2.5-1.5B-Instruct architecture. This 1.5 billion parameter model has been extensively fine-tuned on a large corpus of Chinese erotic literature and sensitive datasets, including "Bad Data," "Toxic-All," and "Erotic Literature Collection." Its training focus makes it particularly adept at generating content related to these themes, with a strong emphasis on Chinese text due to the primary language of its training data.
Key Capabilities
- Specialized Content Generation: Optimized for producing text within the domains of erotic literature and sensitive topics.
- Chinese Language Proficiency: Demonstrates enhanced performance when processing and generating Chinese text due to its dataset composition.
- Continuous Dialogue: Supports multi-turn conversations, as demonstrated by the provided Python inference script.
Intended Use and Limitations
This model is explicitly designated for research and testing purposes only. Users are cautioned to adhere to local laws and regulations and assume full responsibility for their actions when utilizing the model. The developers disclaim responsibility for any misuse. The model's 32768 token context length allows for handling relatively long inputs and generating detailed responses.