insilicomedicine/Qwen3-1.7B-Longevity
insilicomedicine/Qwen3-1.7B-Longevity is a 2 billion parameter, decoder-only transformer model developed jointly by Insilico Medicine and Liquid AI. It is a domain-adapted language model, fine-tuned from Qwen/Qwen3-1.7B, specifically designed for interpreting heterogeneous aging biology data with a context length of 32,768 tokens. This model excels at tasks related to aging biology and multi-omics interpretation, making it suitable for research in these specialized fields.
Loading preview...
Longevity-LLM: Qwen3-1.7B-Longevity
Longevity-LLM (L-LLM) is a specialized family of compact, domain-adapted language models developed by Insilico Medicine and Liquid AI. This particular checkpoint, L-Qwen3-1.7B, is a 2 billion parameter, decoder-only transformer model, fine-tuned from Qwen/Qwen3-1.7B.
Key Capabilities
- Domain Adaptation: Specifically fine-tuned on aging-related multi-omics and clinical data, making it highly proficient in this niche.
- Extended Context: Features a substantial context length of 32,768 tokens, enabling the processing of extensive biological datasets.
- Multitask Instruction-Tuned: Designed for various tasks within aging biology, leveraging a dynamic-thinking template for inference.
- Research-Oriented: Developed as part of the study "An Open Benchmark and Language Models for AI in Aging Biology" (Zhavoronkov et al., 2026).
Good For
- Interpreting Aging Biology Data: Ideal for analyzing and interpreting complex, heterogeneous data related to aging.
- Multi-omics Research: Particularly strong in tasks involving multi-omics data within the longevity domain.
- Academic and Research Applications: Intended for research purposes in aging biology and omics interpretation, not for clinical advice.
- Benchmarking: Can be used in conjunction with the LongevityBench dataset for evaluating models in aging biology.