— Verifier: openai/gpt-oss-120b — Speculative Decoding Algorithm: EAGLE-3 — Model Architecture: Eagle3Speculator — Release Date: 03/10/2026 — Version: 2.0 — Model Developers: RedHat This is a speculator model designed for use with openai/gpt-oss-120b, based on the EAGLE-3 speculative decoding algorithm. It was trained using the speculators library on a combination of the Magpie-Align/Magpie-Llama-3.1-Pro-300K-Filtered dataset and the trainsft split of the HuggingFaceH4/ultrachat200k dataset. Training data used Magpie + UltraChat with responses from the gpt-oss-120b model (reasoning). This model should be used with the openai/gpt-oss-120b chat template, specifically through the /chat/completions endpoint. This draft model uses normbeforefc (pre-FC RMSNorm for gpt-oss Eagle3). INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED BUT SOME MAY HAVE NO CONTENT
Модальности:
Генерация текста
Задача: Генерация текста
Автор: RedHatAI
Теги: neuralmagic, redhat, speculators, eagle3, gpt-oss, custom_code, endpoints_compatible
Лайков: 4 | Загрузок: 2,942
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
