Image-Text-to-Text
Transformers
Safetensors
English
openvla
feature-extraction
robotics
vla
multimodal
pretraining
custom_code
Instructions to use openvla/openvla-v01-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openvla/openvla-v01-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="openvla/openvla-v01-7b", trust_remote_code=True)# Load model directly from transformers import AutoModelForVision2Seq model = AutoModelForVision2Seq.from_pretrained("openvla/openvla-v01-7b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openvla/openvla-v01-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openvla/openvla-v01-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openvla/openvla-v01-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openvla/openvla-v01-7b
- SGLang
How to use openvla/openvla-v01-7b 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 "openvla/openvla-v01-7b" \ --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": "openvla/openvla-v01-7b", "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 "openvla/openvla-v01-7b" \ --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": "openvla/openvla-v01-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openvla/openvla-v01-7b with Docker Model Runner:
docker model run hf.co/openvla/openvla-v01-7b
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "processing_prismatic.PrismaticImageProcessor", | |
| "AutoProcessor": "processing_prismatic.PrismaticProcessor" | |
| }, | |
| "image_processor_type": "PrismaticImageProcessor", | |
| "image_resize_strategy": "letterbox", | |
| "input_sizes": [ | |
| [ | |
| 3, | |
| 224, | |
| 224 | |
| ] | |
| ], | |
| "interpolations": [ | |
| "bicubic" | |
| ], | |
| "means": [ | |
| [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| ], | |
| "processor_class": "PrismaticProcessor", | |
| "stds": [ | |
| [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| ], | |
| "tvf_crop_params": [ | |
| { | |
| "output_size": [ | |
| 224, | |
| 224 | |
| ] | |
| } | |
| ], | |
| "tvf_do_letterbox": true, | |
| "tvf_letterbox_fill": [ | |
| 127, | |
| 127, | |
| 127 | |
| ], | |
| "tvf_normalize_params": [ | |
| { | |
| "inplace": false, | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| } | |
| ], | |
| "tvf_resize_params": [ | |
| { | |
| "antialias": true, | |
| "interpolation": 3, | |
| "max_size": null, | |
| "size": 224 | |
| } | |
| ], | |
| "use_fused_vision_backbone": false | |
| } | |