Instructions to use Sean-xyt/LEGO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sean-xyt/LEGO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Sean-xyt/LEGO") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Sean-xyt/LEGO", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Evaluation results
Checkpoint SHA-256: 7602167b44fadd480b97b034001f6926143946945eb08e066866aecb84a50d07
Reverified on 2026-07-13 with the current run.test release entry point and
the complete local benchmark data.
- AIGIBench (24-subset macro ACC, ProGAN excluded): 0.8021
- Chameleon ACC: 0.8358
- Chameleon AUC: 0.9241
- Chameleon AP: 0.8989
- Chameleon EER: 0.1497
The AIGIBench aggregate follows the paper protocol and excludes ProGAN because that generator family is represented in training. Chameleon is evaluated only after training and is never used for checkpoint selection.