Geneformer
Theodoris LabGeneformer is the Theodoris lab's transformer model pretrained on human single-cell transcriptomes to make context-aware predictions in network biology. It ships 10M, 104M, and 316M-parameter checkpoints plus a cancer-tuned variant, and the same repository carries the tokenizer, the DeepSpeed pretraining example, fine-tuning notebooks, embedding extraction, and in silico perturbation code.
The weights, the code package, and the Genecorpus training data are all distributed from Hugging Face; there is no separate GitHub repository. Verified 2026-09-10 via the Hugging Face API and model card.
Openness
5 high confidence- 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 the full from-scratch release the top rung asks for.
- 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
1 high confidence1,737 downloads in the trailing 30 days for the declared Hugging Face 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.
Capability
3 high confidenceTwo 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.
Verified 2026-09-10