Image-to-Text
Transformers
Safetensors
Malayalam
vision-encoder-decoder
image-text-to-text
ocr
trocr
handwritten-text-recognition
malayalam
indic
Eval Results (legacy)
Instructions to use Artificial-Soul/Devika with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Artificial-Soul/Devika 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="Artificial-Soul/Devika")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Artificial-Soul/Devika") model = AutoModelForMultimodalLM.from_pretrained("Artificial-Soul/Devika", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Artificial-Soul/Devika: direct link, hf CLI and curl.
- Browser
- Download file 325 Bytes
-
https://huggingface.co/Artificial-Soul/Devika/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Artificial-Soul/Devika/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Artificial-Soul/Devika/resolve/main/preprocessor_config.json
325 Bytes
| { | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "ViTImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 384, | |
| "width": 384 | |
| } | |
| } | |