MLMvsCLM

/

610m-mlm40-42k-1000

like 0

Follow

MLMvsCLM 18

This PR adds a comprehensive model card for the text encoder model.
Specifically, it:

• Links the model to its corresponding paper: Should We Still Pretrain Encoders with Masked Language Modeling?.
• Includes the paper's abstract to provide immediate context.
• Adds links to the project page (https://hf.co/MLMvsCLM) and the associated codebase on GitHub (https://github.com/Nicolas-BZRD/EuroBERT).
• Adds essential metadata: pipeline_tag: feature-extraction, library_name: transformers, and license: apache-2.0, making the model discoverable and properly categorized on the Hugging Face Hub.
• Provides a clear Python usage example for feature extraction using the transformers library, including considerations for custom architectures (trust_remote_code) and bfloat16 dtype.
• Includes the correct BibTeX citation for the paper.