swiss-ai/Apertus-8B-Instruct-2509

Revert token 73 to <SPECIAL_73>: <|image|> belongs to the multimodal tokenizers, not this text tokenizer. The chat template keeps referencing it by name and binds against whichever tokenizer ships with an image-capable model.

Add LEXam evaluation results (#32)

Correcting the link for the report. The previous one is obsolete. (#27)

Add support for images and fix end of assistant issue (#22)

remove gating, add policy

Update README.md

Update README.md

Update README.md

Upload tokenizer.json

Update README.md

Update README.md

Update README.md

Create license

Changed model name to Apertus-8B-Instruct-2509 (#1)

initial model card

Update chat_template.jinja

Add files using upload-large-folder tool

upload chat_template, generation and tokenizer configs

Update README.md

initial commit