neuqrui/EOPSA-Qwen3-14B
TEXT GENERATIONPricing:Input $0.48 / Output $0.96Concurrent Unit Cost:1Model Size:14BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 10, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
neuqrui/EOPSA-Qwen3-14B is a 14 billion parameter causal language model, based on the Qwen3 architecture, that has been fine-tuned using the Efficient On-Policy Self-Distilled Safety Alignment (EOPSA) method. This model is specifically optimized for safety alignment, aiming to reduce harmful outputs while maintaining performance. It is designed for applications requiring robust safety features in large language models.
Loading preview...
Overview
neuqrui/EOPSA-Qwen3-14B is a 14 billion parameter language model derived from the Qwen3 architecture, specifically enhanced through the Efficient On-Policy Self-Distilled Safety Alignment (EOPSA) method. This fine-tuning process focuses on improving the model's safety characteristics.
Key Capabilities
- Safety Alignment: Utilizes the EOPSA method to enhance the model's ability to generate safe and appropriate responses.
- Qwen3 Base: Built upon the robust Qwen3-14B foundation, inheriting its general language understanding and generation capabilities.
Training and Resources
- The model's safety alignment was achieved using the EOPSA training code, available on GitHub.
- Related safety evaluations and a collection of EOPSA models can be found in the associated GitHub repository and Hugging Face collection.
Good For
- Applications where safety and responsible AI generation are critical.
- Use cases requiring a Qwen3-based model with enhanced safety features.