Llama-3.3-70B-Instruct-speculator.eagle3

Model Overview

• Verifier: meta-llama/Llama-3.3-70B-Instruct
• Speculative Decoding Algorithm: EAGLE-3
• Model Architecture: Eagle3Speculator
• Release Date: 09/15/2025
• Version: 1.0
• Model Developers: RedHat

This is a speculator model designed for use with meta-llama/Llama-3.3-70B-Instruct, based on the EAGLE-3 speculative decoding algorithm. It was trained using the speculators library on a combination of the Aeala/ShareGPT_Vicuna_unfiltered and the train_sft split of HuggingFaceH4/ultrachat_200k datasets.

Evaluations

Subset of GSM8k (math reasoning):

• acceptance_rate = [0.801, 0.637, 0.464]
• conditional_acceptance_rate = [0.801, 0.795, 0.729]

Subset of MTBench:

• acceptance_rate = [0.733, 0.537, 0.384]
• conditional_acceptance_rate = [0.733, 0.733, 0.715]