TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

An Open Source Toolkit For LLM Distillation

A community supported Windows build for jax.

A collection of learning resources for curious software engineers

Reinforcement Learning for Stock Market Prediction

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Local first semantic code search and chat | Leverage custom copilots with fine-tuning datasets from code in Alpaca, Conversational, Completion and Instruction format

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

Python package for scraping recipes data

A convenient way to search for recipes in marmiton.org

A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

Conformal Decision Theory code

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

Self-hosted AI coding assistant

A real world full-stack application using LlamaIndex

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Implementation of Nougat Neural Optical Understanding for Academic Documents

an example of local large langue model embeddings with Redis as vector stores