Apertus 1.5 Release Notes
• 30
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
Articles
8B and 70B open-data open-weights models, globally multilingual with multimodal input and reasoning support
-
swiss-ai/Apertus-v1.5-8B
Image-Text-to-Text • 9B • Updated • 654k • 145 -
swiss-ai/Apertus-v1.5-70B
Image-Text-to-Text • 72B • Updated • 3.61k • • 122 -
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
Paper • 2610.15542 • Published • 35 -
swiss-ai/Apertus-v1.5-8B-base
Image-Text-to-Text • 9B • Updated • 1.32k • 3
This collection contains datasets used for the continuous pre-training and post-training (SFT, RL and Alignment) of Apertus 1.5.
Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages
-
swiss-ai/Apertus-8B-2509
Text Generation • 8B • Updated • 44.3k • 175 -
swiss-ai/Apertus-8B-Instruct-2509
Text Generation • 8B • Updated • 442k • • 496 -
swiss-ai/Apertus-70B-2509
Text Generation • 71B • Updated • 2.68k • 160 -
swiss-ai/Apertus-70B-Instruct-2509
Text Generation • 71B • Updated • 18.4k • • 194
8B and 70B open-data open-weights models, globally multilingual with multimodal input and reasoning support
-
swiss-ai/Apertus-v1.5-8B
Image-Text-to-Text • 9B • Updated • 654k • 145 -
swiss-ai/Apertus-v1.5-70B
Image-Text-to-Text • 72B • Updated • 3.61k • • 122 -
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
Paper • 2610.15542 • Published • 35 -
swiss-ai/Apertus-v1.5-8B-base
Image-Text-to-Text • 9B • Updated • 1.32k • 3
Collection of checkpoints for the HF transformers integration of the WavTokenizer as part of the Apertus1p5 integration.
This collection contains datasets used for the continuous pre-training and post-training (SFT, RL and Alignment) of Apertus 1.5.
Distillations and Quantizations of our models into more compact formats (<8B parameters)
Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages
-
swiss-ai/Apertus-8B-2509
Text Generation • 8B • Updated • 44.3k • 175 -
swiss-ai/Apertus-8B-Instruct-2509
Text Generation • 8B • Updated • 442k • • 496 -
swiss-ai/Apertus-70B-2509
Text Generation • 71B • Updated • 2.68k • 160 -
swiss-ai/Apertus-70B-Instruct-2509
Text Generation • 71B • Updated • 18.4k • • 194