ianderrington

GP4A

Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"

DoctorGPT

💻📚💡 DoctorGPT provides advanced LLM prompting for PDFs and webpages.

outlines

Structured Text Generation

agent-protocol

Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

gpt-llm-trainer

LangSynth

Conduct consumer interviews with synthetic focus groups using LLMs and LangChain

fabric

llm_multiagent_debate

ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate

dynalang

Code for "Learning to Model the World with Language."

MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

ToolBench

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

MetaTransformer

Meta-Transformer for Unified Multimodal Learning

pr-agent

🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

guardrails

Adding guardrails to large language models.

DemoGPT

Create 🦜️🔗 LangChain apps by just using prompts🌟 Star to support our work! | 只需使用句子即可创建 LangChain 应用程序。 给个star支持我们的工作吧！

app

Issue tracker for the Sourcegraph app - a lightweight single-binary version of Sourcegraph for your local machine

langchain

🦜🔗 Build context-aware reasoning applications

developer

the first library to let you embed a developer agent in your own app!

RL4LMs

A modular RL library to fine-tune language models to human preferences

lanarky

The web framework for building LLM microservices

rebuff

LLM Prompt Injection Detector

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

tokenmonster

Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

camel

🐫 CAMEL: Finding the Scaling Law of Agents. A multi-agent framework. https://www.camel-ai.org

loopgpt

Modular Auto-GPT Framework

Plan-and-Solve-Prompting

Code for our ACL 2023 Paper "Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models".

scGPT

recurrent-memory-transformer

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

guided-diffusion