Meta's latest collection of multimodal models.
771.8K Pulls 11 Tags Updated 4 months ago
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
740.6K Pulls 5 Tags Updated 4 months ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
443.6K Pulls 5 Tags Updated 8 months ago
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
367.5K Pulls 5 Tags Updated 7 months ago