| --- |
| 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 |
