tommybark's Projects
PyBites Code Challenges
Tools for studying developmental interpretability in neural networks.
Keeping language models honest by directly eliciting knowledge encoded in their activations. Building on "Discovering latent knowledge in language models without supervision" (Burns et al. 2022)
Based on primer.ought.org
A repo containing GitHub for programmatic examples
Interactive Composition Explorer: a debugger for compositional language model programs
Free MLOps course from DataTalks.Club
Materials for the Deep Learning -- ÚFAL course NPFL114
NPFL122 repository
A Portable Graphic Format for TeX
Financial portfolio optimisation in python, including classical efficient frontier and advanced methods.
The course site for the Data Processing in Python from IES
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Python package for scraping and analysis of flat market
This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"