The following steps are required to install and configure Skywork-R1V:
environmental preparation
- software dependency: requires Python 3.8+ and Git tools
- Hardware Recommendations: NVIDIA GPUs are recommended, with CUDA and cuDNN acceleration libraries installed
- system requirements: At least 16GB of RAM
Installation process
- Clone the code repository:
git clone https://github.com/SkyworkAI/Skywork-R1V.git - Install the dependencies:
pip install -r requirements.txt - Download model files (approx. 38GB): can be downloaded manually through the Hugging Face website or use the
huggingface-clicommand - Set GPU environment variables (optional):
export CUDA_VISIBLE_DEVICES="0,1"
Note: Although the CPU environment can be run, the inference speed will be significantly reduced. For complex tasks, a multi-GPU configuration is recommended.
This answer comes from the articleSkywork-R1V: A Graphical Hybrid Multimodal Reasoning Model Open Source by Kunlun WanwenThe
May not be reproduced without permission:AI productivity tools " How to install and configure Skywork-R1V and what hardware requirements do I need to fulfill?
