Image-to-Text
Transformers
Safetensors
Hindi
vision-encoder-decoder
image-text-to-text
image caption
Instructions to use BhashaAI/hindi-image-caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BhashaAI/hindi-image-caption 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="BhashaAI/hindi-image-caption")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("BhashaAI/hindi-image-caption") model = AutoModelForMultimodalLM.from_pretrained("BhashaAI/hindi-image-caption", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from BhashaAI/hindi-image-caption: direct link, hf CLI and curl.
- Browser
- Download file 5.3 kB
-
https://huggingface.co/BhashaAI/hindi-image-caption/resolve/main/training_args.bin
- Command line
-
hf download hf://BhashaAI/hindi-image-caption/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/BhashaAI/hindi-image-caption/resolve/main/training_args.bin
5.3 kB
- Xet hash:
- 26d135038559b4a93ec9d9b3cc1506a10fd35d9067c3cf6f47957c4858531820
- Size of remote file:
- 5.3 kB
- SHA256:
- f1491dd3d6e870635fffcfcbcb5e57e563ceebd033d57761ef76fee5137a2251
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.