Video-Text-to-Text
Transformers
Safetensors
English
Chinese
internvideo3
text-generation
video-understanding
multimodal
long-video
agent
custom_code
Instructions to use yanziang/InternVideo3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yanziang/InternVideo3-8B-Instruct with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("yanziang/InternVideo3-8B-Instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from yanziang/InternVideo3-8B-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 877 Bytes
-
https://huggingface.co/yanziang/InternVideo3-8B-Instruct/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://yanziang/InternVideo3-8B-Instruct/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/yanziang/InternVideo3-8B-Instruct/resolve/main/preprocessor_config.json
877 Bytes
| { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "disable_grouping": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": null, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessorFast", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "max_pixels": null, | |
| "merge_size": 2, | |
| "min_pixels": null, | |
| "pad_size": null, | |
| "patch_size": 16, | |
| "processor_class": "InternVideo3Processor", | |
| "auto_map": { | |
| "AutoProcessor": "processing_internvideo3.InternVideo3Processor" | |
| }, | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |