nyu-visionx/cambrian-phi3-3b

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

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

Training dataset

• 2.5M Cambrian Alignment Data.
• 7M Cambrian Curated Instruction Tuning Data