40 lines
1009 B
Markdown
40 lines
1009 B
Markdown
|
---
|
|||
|
|
library_name: transformers
|
|||
|
|
license: apache-2.0
|
|||
|
|
license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
base_model:
|
|||
|
|
- Qwen/Qwen3-8B
|
|||
|
|
---
|
|||
|
|
# 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.<br>
|
|||
|
|
The dataset used is the Chinese Distillation Dataset based on Qwen3-235B-2507
|
|||
|
|
<br>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】
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from modelscope import snapshot_download
|
|||
|
|
snapshot_download('JunHowie/Qwen3-8B-Instruct', cache_dir="your_local_path")
|
|||
|
|
```
|