position-specialist-speculative-decoding
/

Speed-E3-Llama3.1-8B-Instruct-vllm

Model card Files Files and versions

Speed-E3-Llama3.1-8B-Instruct-vllm / README.md

position-specialist-speculative-decoding's picture

position-specialist-speculative-decoding

Upload folder using huggingface_hub

4567f56 verified 8 months ago

|

Raw History Blame Contribute Delete

374 Bytes

SPEED: Specialized Position Experts for Efficient Speculative Decoding

This repository provides the model checkpoint for SPEED, a speculative decoding method proposed in the anonymous paper:

SPEED: Specialized Position Experts for Efficient Speculative Decoding

📦 Files

pytorch_model.bin — model weights
config.json — model configuration