FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.
Repository Index
111,085 visible repositories in the index
121–144 of 454 · Most stars
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
- demo
- eagle
- gpt4
- huggingface
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
- large-language-models
- prompt-optimization
- compound-systems
- textual-gradients
Representation learning on large graphs using stochastic graph convolutions.
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
XcodeBenchmark measures the compilation time of a large codebase on iMac, MacBook, and Mac Pro
[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
- data-mixture
- data-science
- data-selection
- data-reweighting
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model
Learn how to design large-scale systems. Prep for the system design interview.
- architecture
- interview
- design
- design-patterns
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Quickly and accurately render even the largest data.
- holoviz
- datashader
- data-visualizations
- rasterization
[KDD'2026] "VideoRAG: Chat with Your Videos"
- large-language-models
- llms
- long-video-understanding
- multi-modal-llms
【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
- instruction-tuning
- large-vision-language-model
- multi-modal
An unnecessarily tiny implementation of GPT-2 in NumPy.
Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
- large-language-models
- llm
- minimax-text-01
- minimax-vl-01
Utils for streaming large files (S3, HDFS, gzip, bz2...)
- python
- s3
- hdfs
- webhdfs
A high-performance distributed training framework for Reinforcement Learning
- reinforcement-learning
- large-scale
- parallelization
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
- agentic
- rlhf
- rlvr
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
- gpt-4
- visual-language-learning
- artificial-inteligence
- deep-learning
Code for the paper "Evaluating Large Language Models Trained on Code"
KiCAD MCP is a Model Context Protocol (MCP) implementation that enables Large Language Models (LLMs) like Claude to directly interact with KiCAD for printed circuit board design.
PyTorch extensions for high performance and large scale training.