Streamlit and LangGraph Intersection Starters, LangGraph with Streamlit, Streamlit with LangGraph

Fully open reproduction of DeepSeek-R1

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

A course on aligning smol models.

Recipes to scale inference-time compute of open models

O1 Replication Journey

A Lightweight Library for AI Observability

Benchmarking library for RAG

The Open Cookbook for Top-Tier Code Large Language Model

🌟 Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)

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

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

LLM training in simple, raw C/CUDA

Parse Python docstrings in various flavors.

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Neumorphism designed Jekyll theme for personal websites, portfolios and resumes.

groq-api-cookbook

Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

A secure authentication module to manage user access in a Streamlit application.

A template repo for Python packages

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Automatically evaluate your LLMs in Google Colab

OpenChat: Advancing Open-source Language Models with Imperfect Data