Oryx-1.5-7B-Image

Model Summary

The Oryx-Image models are 7/34B parameter models trained based on Qwen2.5 language model with a context window of 32K tokens.

Oryx offers an on-demand solution to seamlessly and efficiently process visual inputs with arbitrary spatial sizes and temporal lengths.

• Repository: https://github.com/Oryx-mllm/Oryx
• Languages: English, Chinese
• Paper: https://arxiv.org/abs/2409.12961

Model Architecture

• Architecture: Pre-trained Oryx-ViT + Qwen2.5-7B
• Data: a mixture of 4M image data
• Precision: BFloat16

Hardware & Software

• Hardware: 64 * NVIDIA Tesla A100
• Orchestration: HuggingFace Trainer
• Code: Pytorch

Citation