Image-to-Text
Transformers
Safetensors
Japanese
English
sarashina2_vision
text-generation
multimodal
ocr
document-understanding
vision-language
custom_code
Instructions to use subhash4face/sarashina2.2-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use subhash4face/sarashina2.2-ocr 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="subhash4face/sarashina2.2-ocr", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("subhash4face/sarashina2.2-ocr", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download assets/sample2_md.png from subhash4face/sarashina2.2-ocr: direct link, hf CLI and curl.
- Browser
- Download file 753 kB
-
https://huggingface.co/subhash4face/sarashina2.2-ocr/resolve/main/assets/sample2_md.png
- Command line
-
hf download hf://subhash4face/sarashina2.2-ocr/assets/sample2_md.png
-
curl -L -o sample2_md.png https://huggingface.co/subhash4face/sarashina2.2-ocr/resolve/main/assets/sample2_md.png
753 kB

- Xet hash:
- 9cc7d45b0a4271f437d78a07057721a3c546de97b13b9c3c903534fb2437b049
- Size of remote file:
- 753 kB
- SHA256:
- 47b478e52d905874a9b843be2442e2f4b35a974ef0a77bb4ecd109c090dc7dd4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.