Instructions to use nvidia/KVzap-linear-Qwen3-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/KVzap-linear-Qwen3-32B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/KVzap-linear-Qwen3-32B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card: add pipeline tag, sample usage, and citation
#1
by nielsr HF Staff - opened
This PR improves the model card for KVzap by:
- Adding the
pipeline_tag: otherto metadata for better categorization. - Adding the
arxivID to link the model to the original research paper. - Including a "Usage" section with a code snippet from the GitHub README to demonstrate how to use the model with the
kvpresslibrary and Hugging Facetransformers. - Adding the BibTeX citation for the paper.
Hi Niels, I updated the README for this model to include your modifications (and added more). I will close all the PRs, thanks for the feedback !
simjeg changed pull request status to closed