mrkwanzaa/functionalizer-100M-github-code-python-seed5

1---2tags:3- functionalizer4- tokenizer5- gpt26library_name: transformers7pipeline_tag: text-generation8---9 10## Functionalizer 100M model11This is a 100M example model. Each model is trained on the dataset specified in the name for 50000 epochs with the given seed.12 13The model was trained using the Functionalizer framework. Training code and detailed performance analysis are available: https://github.com/connor-makowski/functionalizer14 15### Running the model16 17To run the model, use the custom tokenizer fork available here: https://github.com/connor-makowski/tokenizers/tree/functionalizer18 19### Citation20 21If you find this model or the Functionalizer framework useful, please cite:22 23```bibtex24@misc{makowski2026functionalizerlosslessfunctionaldecomposition,25      title={The Functionalizer: Lossless Functional Decomposition for Subword Tokenization}, 26      author={Connor Makowski and Willem Guter},27      year={2026},28      eprint={2609.15991},29      archivePrefix={arXiv},30      primaryClass={cs.CL},31      url={https://arxiv.org/abs/2609.15991}, 32}33```