LiquidAI/LFM2-1.2B-Longevity
LFM2-1.2B-Longevity is a 1.2 billion parameter language model developed jointly by Insilico Medicine and Liquid AI, specifically adapted for interpreting heterogeneous aging biology data. This model utilizes a hybrid Liquid architecture with multiplicative gates and short convolutions, featuring a substantial context length of 32,768 tokens. It was fine-tuned on a specialized corpus of aging-related multi-omics and clinical data, making it ideal for research in aging biology and omics interpretation.
Loading preview...
Longevity-LLM: LFM2-1.2B-Longevity
LFM2-1.2B-Longevity is a specialized 1.2 billion parameter language model developed by Insilico Medicine and Liquid AI. It is part of the Longevity-LLM family, designed for interpreting complex aging biology data. This model is a fine-tuned version of LiquidAI/LFM2-1.2B, adapted through full-parameter supervised fine-tuning on a dedicated corpus of aging-related multi-omics and clinical data.
Key Characteristics
- Domain-Adapted: Specifically trained on the L-LLM corpus, which spans aging biology, including genomic, proteomic, and clinical data.
- Architecture: Features a hybrid Liquid model architecture incorporating multiplicative gates and short convolutions.
- Context Length: Supports a long context window of 32,768 tokens, enabling the processing of extensive biological sequences and clinical records.
- Training: Utilizes a ChatML-like format with a dynamic-thinking template for user prompts, allowing for flexible response modes.
Intended Use Cases
- Aging Biology Research: Ideal for researchers working with diverse datasets in aging biology.
- Omics Interpretation: Suited for tasks involving the interpretation of multi-omics data (genomic, proteomic, clinical) related to aging.
It is important to note that model outputs are predictions for research purposes and should not be considered clinical advice, requiring experimental validation.