Qwen2.5-Coder-0.5B-QwQ-draft

A draft model trained for Qwen/QwQ-32B-Preview

vocabulary size of 152064, same as QwQ-32B-Preview (can be used in VLLM directly without any hack)
trained from Qwen/Qwen2.5-Coder-0.5B-Instruct
on PowerInfer/QWQ-LONGCOT-500K 2 epochs
draft acceptance rate above 0.8
up to x2.5 token speed in math problems (33 toks/s vs. 85 toks/s)

Downloads last month: 29

Safetensors

Model size

494M params

Tensor type

F32

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.