Janus-Pro-7B

Parameters

7B

Published

Jan 27, 2025

Janus-Pro-7B is an AI model developed by DeepSeek (China), first published in January 2025. It works in the image generation, vision, language and multimodal domain, on tasks such as image generation, text-to-image and visual question answering.

Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters. It was trained on roughly 3.1B datapoints. Training ran on 8 NVIDIA A100 SXM4 40 GB for about 336 hours.

Access: Open weights (restricted use). Its weights are openly available. It is built on top of DeepSeek LLM 7B,SigLIP 400M. Epoch AI rates the confidence of this record as confident.

Full record

Organization: DeepSeek
Country of organization: China
Domain: Image generation, Vision, Language, Multimodal
Task: Image generation, Text-to-image, Visual question answering
Compute estimation method: Hardware, Operation counting
Parameters: 7,000,000,000
Dataset size: 3.1B
Training hardware: NVIDIA A100 SXM4 40 GB
Chips used: 8
Training time: 336 h
Training power draw: 6.3 kW
Model accessibility: Open weights (restricted use)
Open weights: Yes
Base model: DeepSeek LLM 7B, SigLIP 400M
Epoch confidence: Confident