sail
/

longspec-QwQ-32B-Preview

Text Generation

text-generation-inference

Model card Files Files and versions

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

For training and usage, see the code at https://github.com/sail-sg/LongSpec.

Downloads last month: 11

Safetensors

Model size

0.6B params

Tensor type

F32

·

Paper for sail/longspec-QwQ-32B-Preview

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification

Paper • 2502.17421 • Published Feb 24, 2025