Robotics
Transformers
Safetensors
openvla
feature-extraction
custom_code
8-bit precision
bitsandbytes
Instructions to use chocopan/openvla_oft_plus_int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chocopan/openvla_oft_plus_int8 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForVision2Seq model = AutoModelForVision2Seq.from_pretrained("chocopan/openvla_oft_plus_int8", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from chocopan/openvla_oft_plus_int8: direct link, hf CLI and curl.
- Browser
- Download file 1.65 kB
-
https://huggingface.co/chocopan/openvla_oft_plus_int8/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://chocopan/openvla_oft_plus_int8/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/chocopan/openvla_oft_plus_int8/resolve/main/preprocessor_config.json
1.65 kB
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "processing_prismatic.PrismaticImageProcessor", | |
| "AutoProcessor": "processing_prismatic.PrismaticProcessor" | |
| }, | |
| "image_processor_type": "PrismaticImageProcessor", | |
| "image_resize_strategy": "resize-naive", | |
| "input_sizes": [ | |
| [ | |
| 3, | |
| 224, | |
| 224 | |
| ], | |
| [ | |
| 3, | |
| 224, | |
| 224 | |
| ] | |
| ], | |
| "interpolations": [ | |
| "bicubic", | |
| "bicubic" | |
| ], | |
| "means": [ | |
| [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| ], | |
| "processor_class": "PrismaticProcessor", | |
| "stds": [ | |
| [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| ], | |
| "tvf_crop_params": [ | |
| { | |
| "output_size": [ | |
| 224, | |
| 224 | |
| ] | |
| }, | |
| { | |
| "output_size": [ | |
| 224, | |
| 224 | |
| ] | |
| } | |
| ], | |
| "tvf_do_letterbox": false, | |
| "tvf_letterbox_fill": null, | |
| "tvf_normalize_params": [ | |
| { | |
| "inplace": false, | |
| "mean": [ | |
| 0.484375, | |
| 0.455078125, | |
| 0.40625 | |
| ], | |
| "std": [ | |
| 0.228515625, | |
| 0.2236328125, | |
| 0.224609375 | |
| ] | |
| }, | |
| { | |
| "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, | |
| 224 | |
| ] | |
| }, | |
| { | |
| "antialias": true, | |
| "interpolation": 3, | |
| "max_size": null, | |
| "size": [ | |
| 224, | |
| 224 | |
| ] | |
| } | |
| ], | |
| "use_fused_vision_backbone": true | |
| } | |