stanbiryukov

grok-1

Grok open release

llm.c

LLM training in simple, raw C/CUDA

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

uv

An extremely fast Python package installer and resolver, written in Rust.

dspy

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

rye

a Hassle-Free Python Experience

transformers.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

llrt

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

marimo

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

OLMo

Modeling, training, eval, and inference code for OLMo

ml-mgie

torchtune

A Native-PyTorch Library for LLM Fine-tuning

dbrx

Code examples and resources for DBRX, a large language model developed by Databricks

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

chronos-forecasting

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

testcontainers-python

Testcontainers is a Python library that providing a friendly API to run Docker container. It is designed to create runtime environment to use during your automatic tests.

maxtext

A simple, performant and scalable Jax LLM!

megablocks

evo

DNA foundation modeling from molecular to genome scale

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 24

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

GeneGPT

Code and data for GeneGPT.

text-clustering

Easily embed, cluster and semantically label text datasets

croissant

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

optimistix

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

mandala

A powerful and easy to use Python framework for experiment tracking and incremental computing

earth2mip

Earth-2 Model Intercomparison Project (MIP) is a python framework that enables climate researchers and scientists to inter-compare AI models for weather and climate.

dinosaur

neuralgcm

Hybrid ML + physics model of the Earth's atmosphere