Stars
Training LLMs with QLoRA + FSDP
The NDIF server, which performs deep inference and serves nnsight requests remotely
The nnsight package enables interpreting and manipulating the internals of deep learned models.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Sparse Autoencoder for Mechanistic Interpretability
Using sparse coding to find distributed representations used by neural networks.
Evaluator for the A::B Prompting Challenge
FacTool: Factuality Detection in Generative AI
A collection of benchmarks and datasets for evaluating LLM.
Code for the paper "Evaluating Large Language Models Trained on Code"
List of papers on hallucination detection in LLMs.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Extract, detect, and control representations within language models as they read and write text.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
replication of geometry of truth
Representation Engineering: A Top-Down Approach to AI Transparency
A library for mechanistic interpretability of GPT-style language models
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Allows users to track the market trends
This is a fullstack boilerplate using react/redux on the frontend and node/express on the backend.