!Banner MicroBananaMind-v1 is a very small causal language model trained from scratch on FineWeb-Edu, FineMath, and Cosmopedia-v2. The model has 902,272 parameters and uses a custom 1536-token byte-level BPE tokenizer with digit-aware tokenization It is our smallest model ever that is not just a TinyStories model. MicroBananaMind-v1 uses our digit-aware 1536-token tokenizer. This model uses custom architecture code, so load it with trustremotecode=True.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: BananaMind
Теги: microbanana, causal-lm, language-model, small-language-model, bananamind, fineweb-edu, finemath, cosmopedia-v2
Лайков: 3 | Загрузок: 45
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
