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)# pip install -U transformers accelerate # 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
Commit History
-
Add model card
Verified signatureThis PR adds a comprehensive model card for the K2Sight model. It includes: - A summary of the model and its purpose. - Links to the paper, project page, GitHub repository, and a Hugging Face Space demo. - Relevant metadata: `apache-2.0` license, `transformers` library, and `zero-shot-object-detection` pipeline tag. - A practical Python code usage example for quick model inference. - A citation for the work.e321f52
-
Add metadata (#1)
Verified signature- Add metadata (67385ea74ade77b60a4f7b9af2716064e55be3c7) Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>1c5b75a -
Upload merged model and processor
Verified signatured065e32 -
Upload merged model and processor
Verified signature610d1df
-
Upload merged model and processor
Verified signaturef5e9d20 -
Upload merged model and processor
Verified signatured58c87d -
initial commit
Verified signature94018e6