Unified KV Cache Compression Methods for Auto-Regressive Models
Library for efficiently connecting and optimizing teams of AI agents
MuA multi-agent reinforcement learning environment
Efficient few-shot learning with Sentence Transformers
Open Agent Harness with a built-in personal agent, Ohmo
Open source RAG framework for building scalable modular AI apps
Pluggable SOTA multi-object tracking modules for segmentation
Knowledge Graph Generation from Any Text
Benchmark LLMs by fighting in Street Fighter 3
FAIR Sequence Modeling Toolkit 2
Framework for orchestrating role-playing, autonomous AI agents
TensorFlow is an open source library for machine learning
A lightweight vLLM implementation built from scratch
Evaluate your LLM's response with Prometheus and GPT4
Universal LLM Deployment Engine with ML Compilation
Data processing for and with foundation models
Reverse engineering Gemini's SynthID detection
RF-DETR is a real-time object detection and segmentation
A Repo For Document AI
Training framework for Stable Baselines3 reinforcement learning agents
Natural language workflows for AI agents
Self-evolving autonomous agent framework
Unsupervised Learning for Image Registration
Build multimodal AI applications with cloud-native stack
Test-Time Reinforcement Learning