#58 · Primary category： Foundation Models
cambrian
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
Project last updated：11/07/25
GitHub Stars
2.0K
Forks
140
Contributors
4
License
Apache-2.0
Why we included this project
Cambrian-1 suits anyone building vision-language assistants who wants the whole stack open rather than a hosted API. The models are built around the image side of the task: instead of feeding a language model a generic visual embedding, the project trains several vision encoders and connects them to the language backbone in a vision-first way. You get the weights plus the training and fine-tuning code, and the release also ships a 10M-image dataset and the CV-Bench benchmark for checking visual grounding. It is research software, so expect to run PyTorch yourself; the fit is for teams who want to reproduce the paper's results or retrain a strong open multimodal baseline on their own data.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities