Image-to-Text
Transformers
PyTorch
TensorBoard
vision-encoder-decoder
image-text-to-text
Generated from Trainer
Instructions to use larabe/news with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use larabe/news 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="larabe/news")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("larabe/news") model = AutoModelForMultimodalLM.from_pretrained("larabe/news", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from larabe/news: direct link, hf CLI and curl.
- Browser
- Download file 421 Bytes
-
https://huggingface.co/larabe/news/resolve/refs%2Fpr%2F1/preprocessor_config.json
- Command line
-
hf download hf://larabe/news@refs/pr/1/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/larabe/news/resolve/refs%2Fpr%2F1/preprocessor_config.json
421 Bytes
| { | |
| "do_align_long_axis": false, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_thumbnail": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "DonutImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "DonutProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": [ | |
| 960, | |
| 1280 | |
| ] | |
| } | |