Instructions to use InternScience/StructTable-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InternScience/StructTable-base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" 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("image-to-text", model="InternScience/StructTable-base")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("InternScience/StructTable-base") model = AutoModelForMultimodalLM.from_pretrained("InternScience/StructTable-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from InternScience/StructTable-base: direct link, hf CLI and curl.
- Browser
- Download file 250 Bytes
-
https://huggingface.co/InternScience/StructTable-base/resolve/903be5e453975ffa9549f89c2eece5b015efa3ff/preprocessor_config.json
- Command line
-
hf download hf://InternScience/StructTable-base@903be5e453975ffa9549f89c2eece5b015efa3ff/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/InternScience/StructTable-base/resolve/903be5e453975ffa9549f89c2eece5b015efa3ff/preprocessor_config.json
250 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "image_processor_type": "Pix2StructImageProcessor", | |
| "is_vqa": false, | |
| "max_patches": 4096, | |
| "patch_size": { | |
| "height": 16, | |
| "width": 16 | |
| }, | |
| "processor_class": "Pix2StructProcessor" | |
| } | |