A game theoretic approach to explain the output of any machine learning model.

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

Book about interpretable machine learning

A course on aligning smol models.

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

OmniXAI: A Library for eXplainable AI

Awesome Machine Unlearning (A Survey of Machine Unlearning)

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

PyTorch Implementation of In-Domain GAN Inversion for StyleGAN2

A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

Code related to the paper "Machine Unlearning of Features and Labels"

Notebooks and Code about Generative Ai, LLMs, MLOPS, NLP , CV and Graph databases

Methods for removing learned data from neural nets and evaluation of those methods

Repo of the paper "On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations"

Streamlit demo for A surprisingly effective way to estimate token importances in LLM prompts

Repository for the paper: Explaining Concept Bottleneck Models with Layer-wise Relevance Propagation

RAG Hallucination Detecting By LRP.