This is a fine-tuned version of the ByGPT5 byte tokenized LLM. It was fine-tuned using conversational style sentences mined from the Colossal Clean Crawled Corpus and movie subtitle corpora.
See our EMNLP 2025 paper for details.
- Downloads last month
- 64
Model tree for figmtu/bygpt5-aac
Base model
nllg/bygpt5-medium-en