huawei-csl

/

Qwen3-32B-3bit-SINQ

like 6

Follow

HUAWEI Computing Systems Lab 53

Hi! I'm Niels from the Hugging Face community team.

This PR improves the model card's metadata by:

• Explicitly setting the pipeline_tag to text-generation for better discoverability.
• Linking the repository to the associated paper: SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights.

It also adds a missing import torch to the usage examples to ensure they run correctly. Please review and merge if this looks good!