speakleash/Bielik-Minitron-7B-v3.0-DFlash - Каталог нейросетей
Генерация текста

speakleash/Bielik-Minitron-7B-v3.0-DFlash

Добавлено:
speakleash/Bielik-Minitron-7B-v3.0-DFlash

Bielik-Minitron-7B-v3.0-DFlash is a DFlash draft model designed for use with Bielik-Minitron-7B-v3.0-Instruct. Its development and training were supported by computational grant PLG/2026/019559 and carried out on the Helios supercomputer, providing access to the advanced infrastructure and computational resources required for large-scale machine learning workloads. This is not a standalone language model. It is designed to be paired with the target model in a speculative decoding setup. The model was trained on the same training dataset as the target model, Bielik-Minitron-7B-v3.0-Instruct. Training was performed using a custom implementation built on top of the ALLaMo framework, developed by Krzysztof Ociepa. Developed by: SpeakLeash & ACK Cyfronet AGH Language: Multilingual (32 European languages, optimized for Polish) Model type: Draft model Target model: Bielik-Minitron-7B-v3.0-Instruct License:** Apache License 2.0 This model should be used with an inference server that supports DFlash speculative decoding. Krzysztof OciepaSpeakLeash — project lead, concept design, calibration data preparation, training pipeline development, and draft model delivery. …

Модальности:
Генерация текста

Области применения:
Мультиязычность


Задача: Генерация текста
Автор: speakleash
Теги: qwen3, dflash, speculative-decoding, block-diffusion, draft-model, efficiency, bielik, diffusion-language-model
Лайков: 4  |  Загрузок: 166

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.