Model Gallery

4 models from 1 repositories

Filter by type:

Filter by tags:

carbon-3b-q4
Carbon-3B is Hugging Face's 3B-parameter genomic foundation model for DNA and RNA sequence generation, recovery, variant-effect prediction, and motif-perturbation analysis. It supports 32,768 tokens natively and uses a hybrid tokenizer with 6-mer DNA tokens. This default entry uses the Q4_K_M GGUF. A higher-quality Q8_0 build is available as a variant. Prefix DNA sequences with `` and use uppercase A, C, G, and T characters in groups of six.

Repository: localaiLicense: apache-2.0

carbon-3b-q8
Carbon-3B in the higher-quality Q8_0 GGUF format for genomic sequence generation and analysis.

Repository: localaiLicense: apache-2.0

carbon-8b-q4
Carbon-8B is the largest model in Hugging Face's Carbon family of genomic foundation models. It targets DNA and RNA sequence generation, recovery, variant-effect prediction, and motif-perturbation analysis with a native context length of 32,768 hybrid 6-mer DNA tokens. This default entry uses the Q4_K_M GGUF. A higher-quality Q8_0 build is available as a variant. Prefix DNA sequences with `` and use uppercase A, C, G, and T characters in groups of six.

Repository: localaiLicense: apache-2.0

carbon-8b-q8
Carbon-8B in the higher-quality Q8_0 GGUF format for genomic sequence generation and analysis.

Repository: localaiLicense: apache-2.0