Image-to-Text
Transformers
TensorBoard
Safetensors
Icelandic
English
git
image-text-to-text
Generated from Trainer
Instructions to use Sigurdur/isl-img2text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sigurdur/isl-img2text 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="Sigurdur/isl-img2text")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Sigurdur/isl-img2text") model = AutoModelForMultimodalLM.from_pretrained("Sigurdur/isl-img2text") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- b28780b0c4ccf278b419a42c2ab15b478582bfb506aa0f1ee9ff8f05d8504802
- Size of remote file:
- 4.67 kB
- SHA256:
- bb7a90aa348858d72c9e108d7bcd2cbe0e005f70e0d2d19cee64f97135504145
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.