GrimSqueaker/ProtSent-V2-150M
https://huggingface.co/GrimSqueaker/ProtSent-V2-150MContrastively 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.
Sourced from
- HuggingFace — GrimSqueaker/ProtSent-V2-150M
Related resources
GrimSqueaker/ProtSent-V2-ESMC-300M
by GrimSqueakerContrastively fine-tuned ESM-C 300M producing fixed-length protein embeddings where biological similarity maps to embedding proximity. Intended for retrieval, clustering, and nearest-neighbour transfer.
GrimSqueaker/ProtSent-V2.5-35M
by GrimSqueakerProtSent-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.
The ESMC scaling-study checkpoints are being released to support reproducibility of the findings in our paper, please refer to the paper and github for details. Please use the ESMC model for research work. ESMC is a state-of-the-art protein language model trained on billions of protein sequences…
This model card provides an overview of the intended use of the ESMC SAE models and examples of how to access them, but it does not have a specific model or model weights. To access each SAE model collection, use the links below: