PengJiaMa123/RAMER

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:

MIMIC is a multimodal encoder–decoder foundation model of the central dogma, trained jointly over DNA, RNA, and protein together with a range of structural and functional tracks. A single model embeds any subset of modalities into a shared representation space and generates any modality conditioned…

ProCyon-Full is a multimodal foundation model for protein phenotypes, which combines a large language model with protein encoders to support inputs of interleaved free text and proteins. This model is instruction-tuned using the full ProCyon-Instruct dataset.

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

GeneJEPA is a Joint-Embedding Predictive Architecture (JEPA) trained for self-supervised representation learning on scRNA-seq. It uses a Perceiver-style encoder to handle sparse, high-dimensional gene count vectors and a Fourier-feature tokenizer for numerical tokenization.

esm3-sm-open-v1 is trained on 2.78 billion natural proteins. With synthetic data augmentation, this led to 3.15 billion protein sequences, 236 million protein structures, and 539 million proteins with function annotations, totaling 771 billion tokens.