Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
MOSS-VL
image-understanding
video-understanding
bitsandbytes
NF4
quantized
custom_code
4-bit precision
Instructions to use OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Instruct-0708-NF4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_moss_vl.MossVLProcessor", | |
| "AutoVideoProcessor": "video_processing_moss_vl.MossVLVideoProcessor" | |
| }, | |
| "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": null, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "max_frames": 256, | |
| "merge_size": 2, | |
| "min_frames": 1, | |
| "num_extract_threads": 4, | |
| "num_frames": null, | |
| "pad_size": null, | |
| "patch_size": 16, | |
| "processor_class": "MossVLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 4096 | |
| }, | |
| "temporal_patch_size": 1, | |
| "video_fps": 1.0, | |
| "video_max_pixels": 201326592, | |
| "video_metadata": null, | |
| "video_processor_type": "MossVLVideoProcessor" | |
| } | |