neuqrui/safe-rlsd-qwen3-4B
TEXT GENERATIONConcurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 20, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The neuqrui/safe-rlsd-qwen3-4B is a 4 billion parameter language model based on the Qwen3 architecture, developed by neuqrui. It features a context length of 32768 tokens and is specifically safety-finetuned using the RLSD method. This model is designed for applications requiring robust safety measures in language generation.
Loading preview...
Model Overview
The neuqrui/safe-rlsd-qwen3-4B is a 4 billion parameter model built upon the Qwen3 architecture, offering a substantial context window of 32768 tokens. Its primary distinguishing feature is its safety-finetuning using the RLSD (Reinforcement Learning from Safe Demonstrations) method.
Key Capabilities
- Enhanced Safety: The model has undergone specific finetuning to improve its safety characteristics, making it suitable for sensitive applications.
- Qwen3 Architecture: Leverages the robust and efficient Qwen3 base model for strong language understanding and generation.
- Extended Context: A 32768-token context length allows for processing and generating longer, more complex texts while maintaining coherence.
Good For
- Applications requiring content moderation: Its safety finetuning makes it a strong candidate for use cases where harmful or undesirable outputs need to be minimized.
- Safe AI assistants: Developing conversational agents or chatbots that prioritize safe and ethical responses.
- Research into safety alignment: Provides a base model for further experimentation and development in AI safety techniques.