position-specialist-speculative-decoding
/

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

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

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

Downloads last month: 22

Safetensors

Model size

0.9B params

Tensor type

I64

·

BF16

·

BOOL

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support