Cambrian-1-8B

Parameters

8B

Published

Jun 24, 2024

Cambrian-1-8B is an AI model developed by New York University (NYU) (United States), first published in June 2024. It works in the multimodal, vision and language domain, on tasks such as image captioning, visual question answering and character recognition (ocr).

Epoch AI has no training-compute estimate for this model. The model has 8,000,000,000 parameters. Training ran on 512 Google TPU v4.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of LLaMA-3-Instruct-8B. The reference paper has 802 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: New York University (NYU)
Country of organization: United States
Domain: Multimodal, Vision, Language
Task: Image captioning, Visual question answering, Character recognition (OCR)
Parameters: 8,000,000,000
Training hardware: Google TPU v4
Chips used: 512
Training power draw: 343.6 kW
Numerical format: FP32
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: LLaMA-3-Instruct-8B
Citations: 802
Epoch confidence: Confident