Downloads · 30 days
183
87% of all-time downloads
position-specialist-speculative-decoding
Speed-E3-Llama3.1-8B-Instruct-vllm
position-specialist-speculative-decoding/Speed-E3-Llama3.1-8B-Instruct-vllm
Speed-E3-Llama3.1-8B-Instruct-vllm is a machine learning model from position-specialist-speculative-decoding. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository provides the model checkpoint for SPEED, a speculative decoding method proposed in the anonymous paper:
All-time downloads
211
Public
Parameters
911M
1.8 GB on disk
Likes
9
Trending 2
Repo makeup
Click a slice to open those files.
.safetensors1.8 GB · 100%
Parameter types
How the weights are stored.
BF16911M · 100%
Model card
From the Hugging Face model README
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 weightsconfig.json— model configuration
- Type
- llama
- Created
- Jan 28, 2026
- Updated
- Jan 28, 2026