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 breezedeus/pix2text-mfr-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use breezedeus/pix2text-mfr-1.5 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="breezedeus/pix2text-mfr-1.5")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("breezedeus/pix2text-mfr-1.5") model = AutoModelForMultimodalLM.from_pretrained("breezedeus/pix2text-mfr-1.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download decoder_model.onnx from breezedeus/pix2text-mfr-1.5: direct link, hf CLI and curl.
- Browser
- Download file 32 MB
-
https://huggingface.co/breezedeus/pix2text-mfr-1.5/resolve/main/decoder_model.onnx
- Command line
-
hf download hf://breezedeus/pix2text-mfr-1.5/decoder_model.onnx
-
curl -L -o decoder_model.onnx https://huggingface.co/breezedeus/pix2text-mfr-1.5/resolve/main/decoder_model.onnx
32 MB
- Xet hash:
- 51fed330fbb8ecb9301c24a9a67c3dd6c22f65a58d1baf9ca31d8296e2c9a099
- Size of remote file:
- 32 MB
- SHA256:
- 917deb98e91a0453c5f234f58a0f32f9fb037de8527c7eb4ed394daf9e692f2a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.