Highlights
- Pro
-
introspective-awareness Public
Replicating results from "Emergent Introspective Awareness in Large Language Models"
-
-
ai-agents Public
A repository of AI agents that I use for my daily tasks.
-
transformer-from-scratch Public
Building, training, and testing your own GPT-2 style transformer.
-
Distinguishing between faithful and unfaithful CoTs in reasoning models using mechanistic interpretability.
-
An experimental repository trying to understand reasoning models.
-
attention-mechanisms Public
Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.
-
self-supervision Public
Implementations of several self-supervised pretext tasks for language and vision modalities in PyTorch.
-
Comparatively fine-tuning pretrained BERT models on downstream, text classification tasks with different architectural configurations in PyTorch.
-
simple-speech-features Public
Simple, straight-forward extraction of acoustic and prosodic features from sound waves based on Praat and Parselmouth.
-
exemplary-ml-pipeline Public
Exemplary, annotated machine learning pipeline for any tabular data problem.
-
python-interview-review Public
Data structures & algorithms implementations in Python in light of preparing for interviews.
-
blackjack-with-gui Public archive
A Blackjack game with GUI written in Java.