Ifigeneia Apostolopoulou
ifaposto
AI & ML interests
approximate inference, probabilistic models, uncertainty quantification, generative models
Recent Activity
posted an update about 24 hours ago
I’ve uploaded a minimal, self-contained implementation of manual autograd for a transformer-based classifier in PyTorch. It can help build intuition for what autograd is doing under the hood and is a useful hands-on reference for low-level differentiation in Transformer models, such as writing custom backward passes and tracing how gradients flow through attention blocks.
🐙 GitHub:
https://github.com/ifiaposto/transformer_custom_autograd/tree/main
📓 Colab:
https://colab.research.google.com/drive/1Lt7JDYG44p7YHJ76eRH_8QFOPkkoIwhn published an article about 1 year ago
Online Batch Size Adaptation in Hugging Face TrainerOrganizations
None yet