Downloads · 30 days
13
4% of all-time downloads
Oryx-34B-Image
THUdyh/Oryx-34B-Image
Oryx-34B-Image is a text generation model from THUdyh. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
The Oryx-Image models are 7/34B parameter models trained on Oryx-Image-Data, based on Qwen2 language model with a context window of 32K tokens.
All-time downloads
337
Public
Parameters
34.9B
69.8 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors69.8 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- oryx_llama
- Access
- Public
- Created
- Sep 19, 2024
- Updated
- Sep 23, 2024
- SHA
- b9712496
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Oryx-34B-Image
Model Summary
The Oryx-Image models are 7/34B parameter models trained on 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 + Yi-1.5-34B
- Data: a mixture of 4M image data
- Precision: BFloat16
Hardware & Software
- Hardware: 64 * NVIDIA Tesla A100
- Orchestration: HuggingFace Trainer
- Code: Pytorch
Citation
- Task
- Text Generation
- Type
- oryx_llama
- License
- apache-2.0
- Languages
- en, zh
- Created
- Sep 19, 2024
- Updated
- Sep 23, 2024