Video-Text-to-Text
Transformers
Safetensors
English
Chinese
video_mllama
text-generation
multimodal
video
vision-language
mllama
streaming
realtime
low-latency
custom_code
Instructions to use OpenMOSS-Team/moss-video-preview-realtime-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/moss-video-preview-realtime-sft with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("OpenMOSS-Team/moss-video-preview-realtime-sft", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_video_mllama.VideoMllamaImageProcessor", | |
| "AutoProcessor": "processing_video_mllama.VideoMllamaProcessor" | |
| }, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_processor_type": "VideoMllamaImageProcessor", | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "max_image_tiles": 1, | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 560, | |
| "width": 560 | |
| }, | |
| "video_fps": 1.0, | |
| "video_minlen": 8, | |
| "video_maxlen": 256, | |
| "frame_extract_num_threads": 4, | |
| "extract_frame_func": "cv2" | |
| } | |