Training Sparse Autoencoders on Language Models

nannyml: post-deployment data science in python

Everything about the SmolLM & SmolLM2 family of models

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

Easy and flexible data contracts

Python package implementing transformers for pre processing steps for machine learning.

Extra blocks for scikit-learn pipelines.

A Python module to perform exploratory & confirmatory factor analyses.

RAG that intelligently adapts to your use case, data, and queries

Create sparse and accurate risk scoring systems!

Friedman's H-statistics

A Python package with explanation methods for extraction of feature interactions from predictive models

A library for mechanistic interpretability of GPT-style language models

Faker is a Python package that generates fake data for you.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Access large language models from the command-line

DSPy: The framework for programming—not prompting—language models

Build and query dynamic, temporally-aware Knowledge Graphs

Create knowledge graphs with LLMs

🌳 React component to create interactive D3 tree graphs

Model interpretability and understanding for PyTorch

Helps you build better AI agents through debuggable unit testing

Lightweight, lazy model experiment logging

GBM implementation on Legate

Explore and interpret large embeddings in your browser with interactive visualization! 📍

Coming soon

The LLM Evaluation Framework