Instructions to use RioJune/AG-KD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RioJune/AG-KD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-object-detection", model="RioJune/AG-KD", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("RioJune/AG-KD", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("RioJune/AG-KD", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Fixed README.md
#4
by shantam00 - opened
Fix 1 -> The originally imported library AutoModel does not work for this model. AutoModelForCausalLM is the correct one.
Fix 2 -> The original code uses an object detection token (OD) for abnormality grounding. The correct token to be used for abnormality grounding is (CAPTION_TO_PHRASE_GROUNDING) along with the abnormality and the definition as input.