Robotics
Transformers
Safetensors
English
prts_qwen3_vl
feature-extraction
vision-language-action
vla
contrastive-reinforcement-learning
goal-conditioned-rl
qwen3-vl
prts
custom_code
Instructions to use TeleEmbodied/PRTS-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeleEmbodied/PRTS-4B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TeleEmbodied/PRTS-4B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": true, | |
| "fps": 2.0, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "max_frames": 8, | |
| "merge_size": 2, | |
| "min_frames": 4, | |
| "num_frames": null, | |
| "pad_size": null, | |
| "patch_size": 16, | |
| "processor_class": "PRTS_Qwen3VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "longest_edge": 147456, | |
| "shortest_edge": 65536 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_metadata": null, | |
| "video_processor_type": "Qwen3VLVideoProcessor" | |
| } | |