Instructions to use TareHimself/manga-ocr-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TareHimself/manga-ocr-base 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="TareHimself/manga-ocr-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("TareHimself/manga-ocr-base") model = AutoModelForMultimodalLM.from_pretrained("TareHimself/manga-ocr-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update preprocessor_config.json
Verified signature16f7d8f
-
Adding `safetensors` variant of this model (#1)
- Adding `safetensors` variant of this model (f0487a5b5766647de95b538775751af9c427a365) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>c49493d
-
Update preprocessor_config.json
0a1b409 -
Update README.md
977f308 -
Duplicate from kha-white/manga-ocr-base
Co-authored-by: Maciej Budyś <kha-white@users.noreply.huggingface.co>fd80248