Add model card for Image Tokenizer Needs Post-Training
#2
by
nielsr
HF Staff
- opened
This PR significantly improves the model card for "Image Tokenizer Needs Post-Training" by:
- Adding the
pipeline_tag: image-feature-extraction, which helps users discover this model on the Hub at https://huggingface.co/models?pipeline_tag=image-feature-extraction. - Including direct links to the paper (Image Tokenizer Needs Post-Training), the official project page (https://qiuk2.github.io/works/RobusTok/index.html), and the GitHub repository (https://github.com/qiuk2/RobusTok).
- Enriching the model card content by incorporating the paper abstract, key highlights, model zoo, installation instructions, training procedures, and inference commands directly from the original GitHub README.
- Adding relevant visualizations and the BibTeX citation.
Per guidelines, library_name and license tags have not been added as no explicit evidence was found in the provided documentation (GitHub README, paper abstract). Furthermore, no custom Python code snippet for sample usage was generated; instead, the original shell commands for training and inference from the GitHub repository are provided to comply with the "Do not make up code yourself" disclaimer.