AIHugging Faceabout 7 hours ago
Apertus 1.5 Adds Multimodal Reasoning
9 min read
Hugging Face releases Apertus 1.5, a pretraining update adding 4 trillion tokens to the 8B model and 2 trillion to the 70B model for a total of 19T and 17T. The models feature native multimodal understanding of images and audio alongside text, a thinking mode for reasoning, and a context window growing to 262,144 tokens.
Level
Hype check
Tap to vote and see what everyone thinks.