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
update dataset link
Browse files
README.md
CHANGED
|
@@ -26,6 +26,11 @@ SCaR enables evaluation of advanced reasoning and compositional tasks in multimo
|
|
| 26 |
- [VIRTUE-2B-SCaR](https://huggingface.co/Sony/VIRTUE-2B-SCaR)
|
| 27 |
- [VIRTUE-7B-SCaR](https://huggingface.co/Sony/VIRTUE-7B-SCaR)
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
## Experimental Results
|
| 30 |
|
| 31 |
### MMEB
|
|
|
|
| 26 |
- [VIRTUE-2B-SCaR](https://huggingface.co/Sony/VIRTUE-2B-SCaR)
|
| 27 |
- [VIRTUE-7B-SCaR](https://huggingface.co/Sony/VIRTUE-7B-SCaR)
|
| 28 |
|
| 29 |
+
## SCaR Dataset
|
| 30 |
+
|
| 31 |
+
- [SCaR-Train](https://huggingface.co/datasets/Sony/SCaR-Train)
|
| 32 |
+
- [SCaR-Eval](https://huggingface.co/datasets/Sony/SCaR-Eval)
|
| 33 |
+
|
| 34 |
## Experimental Results
|
| 35 |
|
| 36 |
### MMEB
|