— Verifier: meta-llama/Llama-3.1-8B-Instruct — Speculative Decoding Algorithm: EAGLE-3 — Model Architecture: Eagle3Speculator — Release Date: 07/27/2025 — Version: 1.0 — Model Developers: RedHat This is a speculator model designed for use with meta-llama/Llama-3.1-8B-Instruct, based on the EAGLE-3 speculative decoding algorithm. It was trained using the speculators library on a combination of the Aeala/ShareGPTVicunaunfiltered and the HuggingFaceH4/ultrachat200k datasets. This model should be used with the meta-llama/Llama-3.1-8B-Instruct chat template, specifically through the /chat/completions` endpoint. Use cases Use Case Dataset Number of Samples Coding HumanEval 168 Math Reasoning gsm8k 80 Text Summarization CNN/Daily Mail 80 Acceptance lengths Use Case k=1 k=2 k=3 k=4 k=5 k=6 k=7 Coding 1.84 2.50 3.02 3.36 3.61 3.83 3.89 Math Reasoning 1.80 2.40 2.83 3.13 3.27 3.40 3.83 Text Summarization 1.70 2.19 2.50 2.78 2.77 2.98 2.99 — temperature: 0.6 — top_p: 0.9 — repetitions: 5 — time per experiment: 3min — hardware: 1xA100 — vLLM version: 0.11.0 — GuideLLM
Модальности:
Генерация текста
Области применения:
Следование инструкциям
Задача: Генерация текста
Автор: RedHatAI
Теги: facebook, meta, llama, llama-3, neuralmagic, redhat, speculators, eagle3
Лайков: 3 | Загрузок: 6,250
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
