Video-Text-to-Text
Transformers
Safetensors
minicpmv
feature-extraction
MiniCPM-V
finetune
MLLM
custom_code
Instructions to use xjtupanda/MiniCPM-V-200K-video-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xjtupanda/MiniCPM-V-200K-video-finetune with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("xjtupanda/MiniCPM-V-200K-video-finetune", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_processor_type": "MiniCPMVImageProcessor", | |
| "auto_map": { | |
| "AutoProcessor": "processing_minicpmv.MiniCPMVProcessor", | |
| "AutoImageProcessor": "image_processing_minicpmv.MiniCPMVImageProcessor" | |
| }, | |
| "processor_class": "MiniCPMVProcessor", | |
| "max_slice_nums": 1, | |
| "scale_resolution": 448, | |
| "patch_size": 14, | |
| "image_feature_size": 96, | |
| "im_start": "<image>", | |
| "im_end": "</image>", | |
| "slice_start": "<slice>", | |
| "slice_end": "</slice>", | |
| "unk": "<unk>", | |
| "norm_mean": [0.5, 0.5, 0.5], | |
| "norm_std": [0.5, 0.5, 0.5], | |
| "version": 2.5 | |
| } | |