Scientific Machine Learning class at CU Boulder, Fall 2024

Optimal transport tools implemented with the JAX framework, to get differentiable, parallel and jit-able computations.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Python-based Derivative-Free Optimization with Bound Constraints

Python-based Derivative-Free Optimizer for Least-Squares

Python solver for large-scale nonlinear least-squares minimization without derivatives

Implementation of direct search for derivative-free optimization

Gaussian processes framework in python

BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.

Representation Engineering: A Top-Down Approach to AI Transparency

MTEB: Massive Text Embedding Benchmark

the AI-native open-source embedding database

Code repository for the paper - "Matryoshka Representation Learning"

Mamba SSM architecture

Benchmarks of approximate nearest neighbor libraries in Python

Bayesian modelling of bipartite networks

A modular graph-based Retrieval-Augmented Generation (RAG) system

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

An extremely fast Python linter and code formatter, written in Rust.

A Node.js style checker and lint tool for Markdown/CommonMark files.

Run your GitHub Actions locally 🚀

Diffusion on syntax trees for program synthesis

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

Python package for pairwise ranking

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

Inspect: A framework for large language model evaluations

Postgres with GPUs for ML/AI apps.

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