Image-to-Text
Transformers
ONNX
vision-encoder-decoder
image-text-to-text
latex-ocr
math-ocr
math-formula-recognition
mfr
pix2text
p2t
Instructions to use kinghtwo/pix2text-mfr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kinghtwo/pix2text-mfr 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="kinghtwo/pix2text-mfr")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("kinghtwo/pix2text-mfr") model = AutoModelForMultimodalLM.from_pretrained("kinghtwo/pix2text-mfr") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 1, | |
| "decoder_start_token_id": 2, | |
| "eos_token_id": 2, | |
| "max_new_tokens": 512, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.37.0", | |
| "use_cache": false | |
| } | |