Stars
official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, LLMs, RAGs, LangChain, LangGraph, Fine-tuning Llama 3 & AI Agents (CrewAI)
Build resilient language agents as graphs.
Implementation of "RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation".
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Code for our ACL 2023 Paper "Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models".
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
ImageBind One Embedding Space to Bind Them All
DSPy: The framework for programming—not prompting—foundation models
LLM based autonomous agent that does online comprehensive research on any given topic
Drag & drop UI to build your customized LLM flow
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Official repository of Evolutionary Optimization of Model Merging Recipes
LILO: Library Induction with Language Observations
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).
We perform functional grounding of LLMs' knowledge in BabyAI-Text
[ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"
[CoRL '23] Dexterous piano playing with deep reinforcement learning.
The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".
Reduce multiple PyTorch TensorBoard runs to new event (or CSV) files.
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.