Caduceus is an Apache-2.0-licensed transformer model for fill-mask prediction on biological sequences, with support for very long sequence lengths. Researchers and developers can download the Safetensors weights and run the model locally or through Hugging Face tooling.
Caduceus Ps Seqlen 131k D Model 256 N Layer 16 is a Foundation models & chat project. It focuses on modeling and filling masked positions in long biological and genomic sequences. It is built as an open-source project for machine learning researchers and computational biologists. Caduceus Ps Seqlen 131k D Model 256 N Layer 16 is open source under the Open Source license. Caduceus Ps Seqlen 131k D Model 256 N Layer 16 is available on the web, API, and the command line, and it can be self-hosted.
It is developed by Kuleshov Group. Key capabilities include fill-mask prediction, long-context modeling, and safetensors weights. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do