| | --- |
| | license: apache-2.0 |
| | datasets: |
| | - THUdyh/Oryx-Image-Data |
| | base_model: |
| | - Qwen/Qwen2-7B-Instruct |
| | pipeline_tag: text-generation |
| | language: |
| | - en |
| | - zh |
| | --- |
| | # Oryx-7B-Image |
| |
|
| | ## Model Summary |
| |
|
| | The Oryx-Image models are 7/34B parameter models trained on [Oryx-Image-Data](https://huggingface.co/datasets/THUdyh/Oryx-Image-Data), based on Qwen2 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](https://huggingface.co/THUdyh/Oryx-ViT) + Qwen2-7B |
| | - **Data:** a mixture of 4M image data |
| | - **Precision:** BFloat16 |
| |
|
| | #### Hardware & Software |
| |
|
| | - **Hardware:** 64 * NVIDIA Tesla A100 |
| | - **Orchestration:** HuggingFace Trainer |
| | - **Code:** Pytorch |
| |
|
| | ## Citation |
