2.3.1

What's new?

New models and tokenizers

• Models:
  • MobileViT for image classification
  • Roberta for token classification (thanks @julien-c)
  • XLMRoberta for masked language modelling, sequence classification, token classification, and question answering
• Tokenizers: FalconTokenizer, GPTNeoXTokenizer

Improved documentation

• Details on how to discover and share transformers.js models on the hub (link)
• Example text-generation code (link)
• Example image-classification code (link)

Misc bug fixes

• Fix conversion to grayscale (commit)
• Aligned .generate() function output with original python implementation
• Fix issue with non-greedy samplers
• Use WASM SIMD on iOS != 16.4.x (thanks @lsb)

New Contributors

• @julien-c made their first contribution in #170
• @lsb made their first contribution in #174

Full Changelog: 2.3.0...2.3.1