cambrian-mllm/cambrian
A family of multimodal large language models that combine vision encoders (DINO, CLIP) with LLMs for vision-language understanding.
Not currently ranked — collecting fresh signals.
star history
Cambrian-1 is a multimodal LLM family designed with a vision-centric approach. It combines language model capabilities with vision encoders to enable visual understanding within language model frameworks. The project includes model weights, training data (Cambrian-10M), and evaluation benchmarks (CV-Bench). Researchers released both base and instruction-tuned model variants with various sizes.
Frequently asked
- What is cambrian-mllm/cambrian?
- A family of multimodal large language models that combine vision encoders (DINO, CLIP) with LLMs for vision-language understanding.
- Is cambrian open source?
- Yes — cambrian-mllm/cambrian is open source, released under the Apache-2.0 license.
- What language is cambrian written in?
- cambrian-mllm/cambrian is primarily written in Python.
- How popular is cambrian?
- cambrian-mllm/cambrian has 2k stars on GitHub.
- Where can I find cambrian?
- cambrian-mllm/cambrian is on GitHub at https://github.com/cambrian-mllm/cambrian.