Instructions to use szang18/spatialvla-pickcube-20k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use szang18/spatialvla-pickcube-20k with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("IPEC-COMMUNITY/spatialvla-4b-224-pt") model = PeftModel.from_pretrained(base_model, "szang18/spatialvla-pickcube-20k") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from szang18/spatialvla-pickcube-20k: direct link, hf CLI and curl.
- Browser
- Download file 512 Bytes
-
https://huggingface.co/szang18/spatialvla-pickcube-20k/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://szang18/spatialvla-pickcube-20k/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/szang18/spatialvla-pickcube-20k/resolve/main/preprocessor_config.json
512 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_spatialvla.SpatialVLAProcessor" | |
| }, | |
| "do_convert_rgb": null, | |
| "do_normalize": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "SiglipImageProcessor", | |
| "image_seq_length": 256, | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "SpatialVLAProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| } | |