README.md

---
license: apache-2.0
---


# Cambrian Model Card

## Model details

**Model type:**
Cambrian is an open-source Multimodal LLM with vision-centric designs.

**Model date:**
Cambrian-1-3B was trained in June 2024.

**Paper or resources for more information:**
- https://cambrian-mllm.github.io/
- https://arxiv.org/abs/2406.16860 

## License
MIT License following Phi-3

## Performance
![Cambrian Results including Cambrian-3B](phi3_results.png)

**Where to send questions or comments about the model:**
https://github.com/cambrian-mllm/cambrian/issues

## Training dataset
- [2.5M Cambrian Alignment Data](https://huggingface.co/datasets/nyu-visionx/Cambrian-Alignment).
- [7M Cambrian Curated Instruction Tuning Data](https://huggingface.co/datasets/nyu-visionx/Cambrian-10M)