Image-to-Text
Transformers
PyTorch
textract
feature-extraction
ocr
vision-language
qwen2-vl
custom-model
text-extraction
document-ai
high-accuracy
custom_code
Instructions to use BabaK07/textract-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BabaK07/textract-ai 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="BabaK07/textract-ai", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BabaK07/textract-ai", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from BabaK07/textract-ai: direct link, hf CLI and curl.
- Browser
- Download file 428 Bytes
-
https://huggingface.co/BabaK07/textract-ai/resolve/main/config.json
- Command line
-
hf download hf://BabaK07/textract-ai/config.json
-
curl -L -o config.json https://huggingface.co/BabaK07/textract-ai/resolve/main/config.json
428 Bytes
| { | |
| "architectures": [ | |
| "FixedTextractAI" | |
| ], | |
| "model_type": "textract", | |
| "base_model": "Qwen/Qwen2-VL-2B-Instruct", | |
| "hidden_size": 1536, | |
| "vocab_size": 152064, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.0", | |
| "auto_map": { | |
| "AutoModel": "modeling_textract.FixedTextractAI", | |
| "AutoConfig": "modeling_textract.TextractConfig" | |
| }, | |
| "_name_or_path": "BabaK07/textract-ai", | |
| "custom_model": true | |
| } |