evildevlive/Qwen3-Sex
Qwen3-Sex is a 4 billion parameter instruction-tuned conversational model developed by evildevlive, based on Qwen/Qwen3-4B-Instruct-2507. It is specifically fine-tuned for generating adult-oriented content and explicit descriptions, with a recommended context length of 4K–32K tokens from its native 262K. This model is intended for users aged 18 and above for non-commercial, academic research, or fictional creation purposes.
Loading preview...
Model Overview
Qwen3-Sex is a 4 billion parameter conversational model, fine-tuned by evildevlive from the Qwen3-4B-Instruct-2507 base model. It is specifically designed and trained to generate adult-oriented content and explicit descriptions, making it suitable for mature audiences (18+) only. The model utilizes bfloat16 data type and supports a native context length of 262,144 tokens, with 4K–32K recommended for daily conversational use.
Key Characteristics
- Base Model: Qwen/Qwen3-4B-Instruct-2507.
- Content Focus: Explicitly fine-tuned for generating adult and sensitive content.
- Context Length: Native support for 262,144 tokens, with practical usage recommended between 4K and 32K.
- Chat Template: Uses the standard ChatML format (
<|im_start|>/<|im_end|>). - Availability: Provided in
safetensors(bfloat16) andGGUFformats (BF16 and Q8_0 quantized).
Intended Use Cases
This model is primarily intended for:
- Academic Research: Studying the generation of adult-oriented text.
- Personal Non-Commercial Use: For individual exploration and experimentation.
- Fictional Creation: Assisting in the generation of explicit narratives or creative writing.
Important Note: Users are strongly advised to adhere to the provided generation_config.json for optimal performance, as these parameters have been specifically tuned for the model's intended output. The model comes with a strict disclaimer regarding its content and usage, emphasizing compliance with legal and ethical guidelines.