Tdamre/limite-1b-violetto-GGUF-LiteRT - Каталог нейросетей
Генерация текста

Tdamre/limite-1b-violetto-GGUF-LiteRT

Добавлено:
Tdamre/limite-1b-violetto-GGUF-LiteRT

Community conversions by Tdamre of Paradigma’s original model, under Apache 2.0. Source revision: e078b5374daa81e477fca61b55b1bfe54c6c9208. Both formats preserve the model’s custom Limite architecture. GGUF runtime requirement: these files require the included Limite llama.cpp patch. Stock llama.cpp/Ollama builds do not implement this architecture at this release. The LiteRT-LM bundles use the standard LiteRT-LM format and were tested with LiteRT-LM 0.17.0 on CPU. Use the CPU backend for these graphs; the tested GPU delegate rejects operations in them. Violetto is a lightly instruction-tuned, single-turn mathematical reasoning model. Its fixed upstream mathematical system prompt is retained. Custom system prompts and tools are rejected by that template; it is not a general chat-assistant conversion. Each GGUF is usable with 16,384, 32,768 or 65,536 token runtime contexts. The original 131,072-position metadata is retained; separate copies of identical weights are unnecessary. Presets specify the requested contexts. These are public Unsloth exporter + model-specific importance-matrix quantizations. The exact private Unsloth Dynamic v2/v3 generator was unavailable, so these are not…

Модальности:
Генерация текста

Области применения:
Математика Логика и рассуждение Диалог / чат


Задача: Генерация текста
Автор: Tdamre
Теги: gguf, litert, litert-lm, quantized, mathematics, reasoning, custom-architecture, endpoints_compatible
Лайков: 3  |  Загрузок: 828

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.