Lists (5)
Stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
11 Lessons to Get Started Building AI Agents
"MiniRAG: Making RAG Simpler with Small and Free Language Models"
Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Investment Research for Everyone, Everywhere.
A curated list of insanely awesome libraries, packages and resources for Quants (Quantitative Finance)
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A simple, easy-to-hack GraphRAG implementation
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Retrieval and Retrieval-augmented LLMs
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
A package for parsing PDFs and analyzing their content using LLMs.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
A curated list of awesome Taichi applications, courses, demos and features.
A quick guide (especially) for trending instruction finetuning datasets
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Productive, portable, and performant GPU programming in Python.
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
An Open-source RL System from ByteDance Seed and Tsinghua AIR