Visual Question Answering
Transformers
Safetensors
English
Hindi
paligemma
image-text-to-text
Bilingual
text-generation-inference
Instructions to use BhashaAI/ViLaH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BhashaAI/ViLaH with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="BhashaAI/ViLaH")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("BhashaAI/ViLaH") model = AutoModelForMultimodalLM.from_pretrained("BhashaAI/ViLaH", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from BhashaAI/ViLaH: direct link, hf CLI and curl.
- Browser
- Download file 17.8 MB
-
https://huggingface.co/BhashaAI/ViLaH/resolve/main/tokenizer.json
- Command line
-
hf download hf://BhashaAI/ViLaH/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/BhashaAI/ViLaH/resolve/main/tokenizer.json
17.8 MB
- Xet hash:
- 5a26021a76ea1a5c2d354a19158faf325ddbde4f2f3b41ff14195fb7f677ebd5
- Size of remote file:
- 17.8 MB
- SHA256:
- f8104de0e0f9b8ab923ac66b31bee4ae132edf05863545fa4a3b69b4774117ae
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.