Video-Text-to-Text
Transformers
Safetensors
qwen2_vl_bev
text-generation
llama-factory
full
Generated from Trainer
spatial-intelligence
3d-vision
Instructions to use Spacewanderer8263/Proxy3D-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Spacewanderer8263/Proxy3D-8B with Transformers:
# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("Spacewanderer8263/Proxy3D-8B", 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_pad": null, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": false, | |
| "fps": null, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "input_data_format": null, | |
| "max_frames": 768, | |
| "max_pixels": 12845056, | |
| "merge_size": 2, | |
| "min_frames": 4, | |
| "min_pixels": 784, | |
| "num_frames": null, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 784 | |
| }, | |
| "size_divisor": null, | |
| "temporal_patch_size": 2, | |
| "video_metadata": null, | |
| "video_processor_type": "Qwen2VLVideoProcessor" | |
| } | |