UCSC-VLAA/STAR1-R1-Distill-1.5B
UCSC-VLAA/STAR1-R1-Distill-1.5B is a 1.5 billion parameter language model developed by UCSC-VLAA, fine-tuned on the STAR-1 dataset to enhance safety alignment in large reasoning models. This model is specifically designed to improve safety practices with minimal impact on reasoning capabilities. It integrates and refines data from multiple sources, providing policy-grounded reasoning samples for safer AI applications.
Loading preview...
Overview
UCSC-VLAA/STAR1-R1-Distill-1.5B is a 1.5 billion parameter model developed by UCSC-VLAA, specifically fine-tuned using the STAR-1 dataset. The STAR-1 dataset is a high-quality safety dataset comprising 1,000 carefully selected examples, designed to improve safety alignment in large reasoning models (LRMs) like DeepSeek-R1. Each example in STAR-1 is aligned with best safety practices, validated through GPT-4o-based evaluation.
Key Capabilities
- Enhanced Safety Alignment: Fine-tuning with STAR-1 significantly improves safety performance across various benchmarks.
- Preserved Reasoning: The safety enhancements are achieved with minimal impact on the model's core reasoning capabilities.
- Policy-Grounded Reasoning: The model benefits from a dataset built on principles of diversity, deliberative reasoning, and rigorous filtering, providing robust policy-grounded reasoning samples.
Good For
- Developers seeking to deploy reasoning LLMs with improved safety characteristics.
- Applications requiring models that adhere to best safety practices without compromising reasoning performance.
- Research into safety alignment techniques for large language models.