Sidharth Baskaran's repositories
ml-sandbox
Deep learning models and paper implementations
aegis
Self-hardening firewall for large language models
hypernetwork-editor
hypernetwork-editor
tensor-saes
An attempt to create SAEs that reconstruct activations across all transformer layers.
context_distillation
taken from https://openreview.net/forum?id=am22IukDiKf
deep-learning-specialization
DeepLearning.AI specialization notes
EasyEdit
An Easy-to-use Knowledge Editing Framework for LLMs.
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
gpuboard
GPU cluster monitoring and auto-shutdown for managed instances on providers like azure, lambda labs, etc.
llm-efficiency-challenge
My attempt and experiments for 2023 NeurIPS LLM Efficiency Challenge
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
machine-learning-coursera
Coursera Machine Learning Repository
meta-interpreters
CS2051 Final Project: On Computability of Meta-Interpreters
paper-tips-and-tricks
Best practice and tips & tricks to write scientific papers in LaTeX, with figures generated in Python or Matlab.
pyreft
ReFT: Representation Finetuning for Language Models
pyvene
Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions
sidnb13.github.io
Personal website
tokengt
[NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch
toolbox
toolbox
ut-aero-research
Repository for UT Aerospace Engineering research internship