Instructions to use siddhantray/Base-StarVLA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use siddhantray/Base-StarVLA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("siddhantray/Base-StarVLA", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download fast/processor_config.json from siddhantray/Base-StarVLA: direct link, hf CLI and curl.
- Browser
- Download file 253 Bytes
-
https://huggingface.co/siddhantray/Base-StarVLA/resolve/main/fast/processor_config.json
- Command line
-
hf download hf://siddhantray/Base-StarVLA/fast/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/siddhantray/Base-StarVLA/resolve/main/fast/processor_config.json
253 Bytes
| { | |
| "action_dim": null, | |
| "auto_map": { | |
| "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor" | |
| }, | |
| "min_token": -354, | |
| "processor_class": "UniversalActionProcessor", | |
| "scale": 10, | |
| "time_horizon": null, | |
| "vocab_size": 2048 | |
| } | |