huawei-csl

/

Qwen3-32B-4bit-ASINQ

like 8

Follow

HUAWEI Computing Systems Lab 53

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

This PR improves the model card by:

• Adding the pipeline_tag: text-generation for better discoverability.
• Adding the arxiv field to the metadata to link the model with its research paper: SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights.
• Adding the missing import torch to the usage and quantization code snippets to ensure they are functional.

Feel free to merge if this looks good!