Original model by Naive AI. This release is built on their work. The Naive AI team created and openly released Naive-N0.5-Flash, including its sparse-attention adaptation, continued pretraining, model weights and reference implementation. Their research and engineering are the foundation of this repository. Many thanks to the team for sharing the model, code and technical details with the community and making derivatives like this possible. Please support and credit the original project: original model · GitHub · technical report and research · Naive AI. Naive’s model in turn builds on Xiaomi MiMo-V2.5-Base and the DeepSeek team’s sparse-attention research. Credit for that foundation belongs to those teams as well. This repository is an unofficial community quantization and serving adaptation: its contribution is the expert-only NVFP4 conversion, validation, and native vLLM integration for RTX PRO Blackwell hardware. NVFP4 expert quantization of NaiveAI/Naive-N0.5-Flash, a sparse-attention derivative of Xiaomi MiMo-V2.5. The model has approximately 309B total parameters and 15.5B active parameters per token. The 49 weight shards occupy 182.57 GB (170.03 GiB). Serve this checkpoint…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: piotrkosecki
Теги: vllm, naive_n05_flash, nvfp4, modelopt, mixture-of-experts, custom-code, blackwell, conversational
Лайков: 3 | Загрузок: 223
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.