Visual Question Answering
Transformers
PyTorch
English
minicpmv
feature-extraction
GUI
Agent
minicpm
custom_code
Instructions to use RhapsodyAI/minicpm-guidance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RhapsodyAI/minicpm-guidance with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="RhapsodyAI/minicpm-guidance", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RhapsodyAI/minicpm-guidance", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from RhapsodyAI/minicpm-guidance: direct link, hf CLI and curl.
- Browser
- Download file 481 Bytes
-
https://huggingface.co/RhapsodyAI/minicpm-guidance/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://RhapsodyAI/minicpm-guidance/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/RhapsodyAI/minicpm-guidance/resolve/main/preprocessor_config.json
481 Bytes
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "processing_minicpmv.MiniCPMVImageProcessor", | |
| "AutoProcessor": "processing_minicpmv.MiniCPMVProcessor" | |
| }, | |
| "image_processor_type": "MiniCPMVImageProcessor", | |
| "processor_class": "MiniCPMVProcessor", | |
| "query_num": 64, | |
| "max_slice_nums": 9, | |
| "scale_resolution": 448, | |
| "patch_size": 14, | |
| "max_inp_length": 2048, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| } | |