A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

[Preprint] Learning to Filter Context for Retrieval-Augmented Generaton

This is an implementation of the paper: Searching for Best Practices in Retrieval-Augmented Generation (EMNLP2024)

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

The example for finetuning chatgpt.

Everything about the SmolLM & SmolLM2 family of models

Public code repo for paper "Aligning LLMs with Individual Preferences via Interaction"

Convert any PDF into a podcast episode!

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

MARS: Mask Attention Refinement with Sequential Quadtree Nodes for Car Damage Instance Segmentation

A tool for LLM-supported authoring and execution of conversational tutoring systems.

An agent benchmark with tasks in a simulated software company.

Code for "Extrinsic Evaluation of Cultural Competence in Large Language Models"

open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act,…

This is Github repo for the paper "NormDial: A Comparable Bilingual Synthetic Dialogue Dataset for Modeling Social Norm Adherence and Violation"

Data and code for the paper "The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems"

Social Chemistry 101: Learning to Reason about Social and Moral Norms

Forward-Looking Active REtrieval-augmented generation (FLARE)

Extracting Cultural Commonsense Knowledge at Scale (WWW 2023)

NormSage: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.