> Quantized release > This repository is an AutoRound W4A16 quantized version of deepreinforce-ai/Ornith-1.0-397B. > It is not the original BF16 model repository. ============================================================ ============================================================ This repository is intended to host the AutoRound W4A16 quantized weights for Ornith-1.0-397B. Benchmark numbers, runtime requirements, and serving recipes in the upstream section below describe the original BF16 model unless explicitly stated otherwise. This model is a quantized derivative of deepreinforce-ai/Ornith-1.0-397B, which is released under the MIT License. The original model card is preserved below for attribution and reference. ============================================================ ============================================================ > The following section is copied from the upstream model card of deepreinforce-ai/Ornith-1.0-397B. > It describes the original BF16 model, not this AutoRound W4A16 quantized release. Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. — State-of-the-Art Coding Agents: Available in…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Pilcothink
Теги: qwen3_5_moe, image-text-to-text, quantized, autoround, auto-round, w4a16, int4, 4-bit
Лайков: 3 | Загрузок: 21
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
