Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Fully open reproduction of DeepSeek-R1

Agentic components of the Llama Stack APIs

Efficient vector database for hundred millions of embeddings.

An Open Large Reasoning Model for Real-World Solutions

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Langchain, Autogen, AG2, and CamelAI

SWIM protocol implementation for exchanging cluster membership status and metadata.

A simple screen parsing tool towards pure vision based GUI agent

Blazingly fast LLM inference.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

A vector search SQLite extension that runs anywhere!

Build and query dynamic, temporally-aware Knowledge Graphs

A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.

A fancy self-hosted monitoring tool

Onnx transformer pipelines in Golang

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

The Data Science Lifecycle Process is a process for taking data science teams from Idea to Value repeatedly and sustainably. The process is documented in this repo.

Tutorial for building LLM router

"Deep Dive into AI with MLX and PyTorch" is an educational initiative designed to help anyone interested in AI, specifically in machine learning and deep learning, using Apple's MLX and Meta's PyTo…

AdalFlow: The library to build & auto-optimize LLM applications.

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

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

Machine Learning Engineering Open Book

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment"

Inspect: A framework for large language model evaluations