CohereLabs/North-Micro-Vision-Instruct

Set tokenizer_class to TokenizersBackend so the tokenizer.json pipeline is used verbatim in transformers v5 (the dedicated CohereTokenizer class hardcodes Digits(individual_digits=True), which does not match this model's trained tokenizer)

Update README.md

delete a trailing comma (#4)

Update config.json (#3)

Add {% generation %} markers for assistant-only loss masking (#2)

Add a response_template for parsing assistant responses (#1)

Update tokenizer_config.json

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit