Containers for machine learning

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

⚡ Dynamically generated stats for your github readmes

This repository collects all relevant resources about interpretability in LLMs

ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).

Tools for understanding how transformer predictions are built layer-by-layer

LLM101n: Let's build a Storyteller

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Solve puzzles. Improve your pytorch.

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

Universal and Transferable Attacks on Aligned Language Models

[ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Code for reproducing our paper "Not All Language Model Features Are Linear"

🟣 LLMs interview questions and answers to help you prepare for your next machine learning and data science interview in 2024.

Machine Learning and Computer Vision Engineer - Technical Interview Questions

A library for efficient patching and automatic circuit discovery.

A JAX research toolkit for building, editing, and visualizing neural networks.

Sparse and discrete interpretability tool for neural networks

ReFT: Representation Finetuning for Language Models

Representation Engineering: A Top-Down Approach to AI Transparency

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

A library for making RepE control vectors