Stars
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…
🦜🔗 Build context-aware reasoning applications
Google Research
LlamaIndex is a data framework for your LLM applications
Statsmodels: statistical modeling and econometrics in Python
Code for "Stochastic Optimization of Sorting Networks using Continuous Relaxations", ICLR 2019.
allRank is a framework for training learning-to-rank neural models based on PyTorch.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
A library to generate LaTeX expression from Python code.
A community-maintained Python framework for creating mathematical animations.
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
What scientific programmers must know about CPUs and RAM to write fast code.
A concise syntax to describe and execute routine data analysis tasks
Flax is a neural network library for JAX that is designed for flexibility.
Folklore facts on probability distribution learning, testing, and whatever-ing
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
A Python-embedded modeling language for convex optimization problems.
A library of reinforcement learning components and agents
Python implementation of the S2 geometry library.
Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE
Run compilers interactively from your web browser and interact with the assembly