Theodoris Lab

weights

open(Apache-2.0 ungated V1-10M, V2-104M, and V2-316M checkpoints)

data

open(Genecorpus-30M and Genecorpus-104M published as Hugging Face datasets)

code

open(tokenization, DeepSpeed pretraining, fine-tuning, and in silico perturbation code in the model repository)

license

Apache-2.0(OSI)

Geneformer publishes the weights, both named pretraining corpora, and a pretraining script in one Apache-2.0 repository, which is a full from-scratch, source-available release.

• https://huggingface.co/api/models/ctheodoris/Geneformer recorded 2026-09-10

  gated: false; private: false; license:apache-2.0 tag; Geneformer-V1-10M, Geneformer-V2-104M, Geneformer-V2-316M, and cancer-tuned safetensors present.

• https://huggingface.co/ctheodoris/Geneformer/raw/main/README.md recorded 2026-09-10

  Links Genecorpus-30M and Genecorpus-104M as released datasets and lists repository functions for tokenizing, pretraining, fine-tuning, embedding extraction, and in silico perturbation.

Adoption is measured as trailing-30-day Hugging Face downloads of the declared repository, which carries every checkpoint in the family.

• https://huggingface.co/api/models/ctheodoris/Geneformer recorded 2026-09-10

  downloads: 1737; gated: false; private: false.

Two attributes are established directly. The long list of downstream fine-tuning tasks is not converted into extra features, the three parameter sizes are not scales, and gene-level and cell-level outputs are treated as one modality rather than two.

• https://huggingface.co/ctheodoris/Geneformer/raw/main/README.md recorded 2026-09-10

  Documents pretraining and fine-tuning examples in the repository, and names in silico perturbation, in silico treatment, in silico reprogramming, and in silico differentiation as applications of the pretrained model.