mrkwanzaa/functionalizer-100M-github-code-python-seed3

1---2library_name: transformers3pipeline_tag: text-generation4tags:5- functionalizer6- tokenizer7- gpt28---9 10## Functionalizer 100M model11 12This model is based on [The Functionalizer: Lossless Functional Decomposition for Subword Tokenization](https://huggingface.co/papers/2609.15991).13 14This is a 100M example model. Each model is trained on the dataset specified in the name for 50000 epochs with the given seed.15 16The model was trained using the Functionalizer framework. Training code and detailed performance analysis are available: https://github.com/connor-makowski/functionalizer17 18### Running the model19 20To run the model, use the custom tokenizer fork available here: https://github.com/connor-makowski/tokenizers/tree/functionalizer21 22### Citation23 24If you find this model or the Functionalizer framework useful, please cite:25 26```bibtex27@misc{makowski2026functionalizerlosslessfunctionaldecomposition,28      title={The Functionalizer: Lossless Functional Decomposition for Subword Tokenization}, 29      author={Connor Makowski and Willem Guter},30      year={2026},31      eprint={2609.15991},32      archivePrefix={arXiv},33      primaryClass={cs.CL},34      url={https://arxiv.org/abs/2609.15991}, 35}36```