Qwen3-8B-Instruct

NOTE：This model is the Instruct-aligned variant, and it will not generate <think></think> blocks in its outputs. Additionally, there is no need to specify enable_thinking=False anymore.

This model was trained using ms-swift as the post-training framework, with full-parameter SFT on 4 × 80GB GPUs.
The dataset used is the Chinese Distillation Dataset based on Qwen3-235B-2507
available at: https://www.modelscope.cn/datasets/swift/Chinese-Qwen3-235B-2507-Distill-data-110k-SFT

【vLLM Startup Command】

vllm serve JunHowie/Qwen3-8B-Instruct 

【Dependencies】

vllm>=0.10.2
transformers>=4.56.1

【Model Download】

from modelscope import snapshot_download
snapshot_download('JunHowie/Qwen3-8B-Instruct', cache_dir="your_local_path")