Minueza-3-95M-Base is a compact English language model with the Gemma 3 architecture, trained from scratch on 1.95 billion tokens. It declares a context length of 8192, which is what the sliding-window layout supports, but every training step ran at 2048 tokens; treat anything past that as extrapolation. At 94.7 million parameters it is a lightweight foundation meant to be fine-tuned, not used as-is. It is distributed only as GGUF, because GGUF was the only weight format used during training: there is no PyTorch checkpoint behind these files. The f32 file is the training master and can continue pretraining; the q80 and q40 files are for inference. Being this small, the model has severe limitations in reasoning and factual knowledge, and will produce fluent text that is frequently wrong. It was trained on web text and can reproduce the biases in it. -hf downloads and caches the weights for you. Swap :Q80 for :Q40 to pull the smaller copy, or -m .gguf to point at a local one. This is a base model: it completes text and has no chat template. The repetition penalty above is not optional, a model this size loops without it. The q4_0 file is 55 MB, small enough to run in a browser tab…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Felladrin
Теги: gguf, gemma3, base-model, en, endpoints_compatible
Лайков: 3 | Загрузок: 101
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
