Robotics
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
fine-tuned
robotics-diffusion-transformer
RDT
rdt
RDT 2
Vision-Language-Action
Bimanual
Manipulation
Zero-shot
UMI
VLA
text-generation-inference
Instructions to use TULLUS/RDT2-VQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TULLUS/RDT2-VQ with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("TULLUS/RDT2-VQ") model = AutoModelForMultimodalLM.from_pretrained("TULLUS/RDT2-VQ", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from TULLUS/RDT2-VQ: direct link, hf CLI and curl.
- Browser
- Download file 575 Bytes
-
https://huggingface.co/TULLUS/RDT2-VQ/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://TULLUS/RDT2-VQ/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/TULLUS/RDT2-VQ/resolve/main/preprocessor_config.json
575 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "max_pixels": 12845056, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |