Image-to-Text
Transformers
TensorBoard
Safetensors
Sinhala
vision-encoder-decoder
image-text-to-text
Instructions to use Ransaka/TrOCR.si with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ransaka/TrOCR.si 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="Ransaka/TrOCR.si")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Ransaka/TrOCR.si") model = AutoModelForMultimodalLM.from_pretrained("Ransaka/TrOCR.si", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from Ransaka/TrOCR.si: direct link, hf CLI and curl.
- Browser
- Download file 4.28 kB
-
https://huggingface.co/Ransaka/TrOCR.si/resolve/main/training_args.bin
- Command line
-
hf download hf://Ransaka/TrOCR.si/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/Ransaka/TrOCR.si/resolve/main/training_args.bin
4.28 kB
- Xet hash:
- 07ee1708ea3a0ac3edc8b0a6eea401b38fd9883e3289e968f1f95e6acc187c6b
- Size of remote file:
- 4.28 kB
- SHA256:
- 88a4fc03b6fcfa54eea14722953f27b1f439dc4a981219a3acd7bde0d41b4575
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.