Instructions to use dacorvo/mnist-mlp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dacorvo/mnist-mlp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dacorvo/mnist-mlp", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dacorvo/mnist-mlp", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add post_init() call for transformers 5.5 compatibility
#3
by pweidel - opened
Calls self.post_init() at the end of MLP.init so the model works correctly with transformers>=5.5, which requires post_init() to properly finalize weight initialization/tying for custom PreTrainedModel subclasses.
dacorvo changed pull request status to merged