Instructions to use Qwen/Qwen3Guard-Stream-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3Guard-Stream-0.6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Qwen/Qwen3Guard-Stream-0.6B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3Guard-Stream-0.6B", trust_remote_code=True) model = AutoModel.from_pretrained("Qwen/Qwen3Guard-Stream-0.6B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag and update paper link
#1
by nielsr HF Staff - opened
This PR improves the model card for Qwen3Guard-Stream-0.6B by:
- Adding the
pipeline_tag: text-classificationto the metadata, which enhances model discoverability on the Hugging Face Hub (e.g., via https://huggingface.co/models?pipeline_tag=text-classification). The model's functionality as a "safety moderation model" and its "token-level classification head" clearly categorize it for text classification. - Updating the paper link to point to the official Hugging Face Papers page: https://huggingface.co/papers/2510.14276, replacing the previous GitHub PDF link.