GrimSqueaker/ProtSent-V2-ESMC-300M

Contrastively fine-tuned ESM-2 150M producing fixed-length protein embeddings where biological similarity maps to embedding proximity. Intended for retrieval, clustering, and nearest-neighbour transfer.

ProtSent-V2 35M plus one more contrastive pass on a fresh draw of the corpus, with a DMS/ProteinGym CoSENT target and a Global Orthogonal Regularization term added.

GeneLinguaLM is a multimodal model that generates natural language descriptions of protein functions from amino acid sequences.

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 31% better perplexity than standard knowledge distillation at 3.8x compression.