Image-to-Text
Transformers
Safetensors
Japanese
English
sarashina2_vision
text-generation
multimodal
ocr
document-understanding
vision-language
custom_code
Instructions to use subhash4face/sarashina2.2-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use subhash4face/sarashina2.2-ocr 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="subhash4face/sarashina2.2-ocr", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("subhash4face/sarashina2.2-ocr", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
File size: 154 Bytes
3c75782 | 1 2 3 4 5 6 7 8 9 | {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 3,
"transformers_version": "4.57.1",
"use_cache": false
}
|