Text Classification
Transformers
PyTorch
English
mechanistic-interpretability
grokking
modular-arithmetic
transformer
TransformerLens
toy-model
Instructions to use BurnyCoder/grokking-modular-multiplication-transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BurnyCoder/grokking-modular-multiplication-transformer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="BurnyCoder/grokking-modular-multiplication-transformer")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BurnyCoder/grokking-modular-multiplication-transformer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download output/svd_analysis.png from BurnyCoder/grokking-modular-multiplication-transformer: direct link, hf CLI and curl.
- Browser
- Download file 462 kB
-
https://huggingface.co/BurnyCoder/grokking-modular-multiplication-transformer/resolve/main/output/svd_analysis.png
- Command line
-
hf download hf://BurnyCoder/grokking-modular-multiplication-transformer/output/svd_analysis.png
-
curl -L -o svd_analysis.png https://huggingface.co/BurnyCoder/grokking-modular-multiplication-transformer/resolve/main/output/svd_analysis.png
462 kB

- Xet hash:
- c6f0ce05cef2a17a436c2fff127477ada49e546032d1ba1b2738dd09f5b142d1
- Size of remote file:
- 462 kB
- SHA256:
- d7f98e04a4addbaa849e8d234455ed184d65a5695e6ebe16dadb8e31c7f2c8f6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.