Instructions to use ICTNLP/StreamUni-Phi4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use ICTNLP/StreamUni-Phi4 with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("<base-model-id>") model.load_adapter("ICTNLP/StreamUni-Phi4", set_active=True) - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from ICTNLP/StreamUni-Phi4: direct link, hf CLI and curl.
- Browser
- Download file 482 Bytes
-
https://huggingface.co/ICTNLP/StreamUni-Phi4/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://ICTNLP/StreamUni-Phi4/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/ICTNLP/StreamUni-Phi4/resolve/main/preprocessor_config.json
482 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_phi4mm.Phi4MMProcessor", | |
| "AutoImageProcessor": "processing_phi4mm.Phi4MMImageProcessor", | |
| "AutoFeatureExtractor": "processing_phi4mm.Phi4MMAudioFeatureExtractor" | |
| }, | |
| "image_processor_type": "Phi4MMImageProcessor", | |
| "processor_class": "Phi4MMProcessor", | |
| "feature_extractor_type": "Phi4MMAudioFeatureExtractor", | |
| "audio_compression_rate": 8, | |
| "audio_downsample_rate": 1, | |
| "audio_feat_stride": 1, | |
| "dynamic_hd": 36 | |
| } | |