Instructions to use Sony/VIRTUE-7B-SCaR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sony/VIRTUE-7B-SCaR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Sony/VIRTUE-7B-SCaR")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Sony/VIRTUE-7B-SCaR") model = AutoModelForMultimodalLM.from_pretrained("Sony/VIRTUE-7B-SCaR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Sony/VIRTUE-7B-SCaR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sony/VIRTUE-7B-SCaR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sony/VIRTUE-7B-SCaR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sony/VIRTUE-7B-SCaR
- SGLang
How to use Sony/VIRTUE-7B-SCaR with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Sony/VIRTUE-7B-SCaR" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sony/VIRTUE-7B-SCaR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Sony/VIRTUE-7B-SCaR" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sony/VIRTUE-7B-SCaR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Sony/VIRTUE-7B-SCaR with Docker Model Runner:
docker model run hf.co/Sony/VIRTUE-7B-SCaR
Download pytorch_model-00001-of-00004.bin from Sony/VIRTUE-7B-SCaR: direct link, hf CLI and curl.
- Browser
- Download file 4.97 GB
-
https://huggingface.co/Sony/VIRTUE-7B-SCaR/resolve/main/pytorch_model-00001-of-00004.bin
- Command line
-
hf download hf://Sony/VIRTUE-7B-SCaR/pytorch_model-00001-of-00004.bin
-
curl -L -o pytorch_model-00001-of-00004.bin https://huggingface.co/Sony/VIRTUE-7B-SCaR/resolve/main/pytorch_model-00001-of-00004.bin
4.97 GB
- Xet hash:
- 466b005d7fd0853a22b6b1f573fe38158eef613ba5ff9f855280aefc5601bc78
- Size of remote file:
- 4.97 GB
- SHA256:
- f41c343aca31558725a37353af8bea47e86e1d1e4be03b56c4f7ec897a4cf955
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.