Hugging Face's logo

sail
/
longspec-longchat-7b-v1.5-32k

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
Community
1

This repository contains the LongSpec model presented in LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification.

Code: https://github.com/sail-sg/LongSpec

Downloads last month
2
Safetensors
Model size
0.3B params
Tensor type
F32
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for sail/longspec-longchat-7b-v1.5-32k