| CARVIEW |
🦍 Gorilla: Large Language Model Connected with Massive APIs
Shishir G.
Patil*,
Tianjun Zhang*,
Xin Wang,
Joseph E. Gonzalez
UC Berkeley
sgp@berkeley.edu, tianjunz@berkeley.edu
Systems and Algorithms for Integrating LLMs with Applications, Tools, and Services
Gorilla Used at
Teach LLM tool use
🎁In OpenFunctions-v2, we natively train the model to support parallel functions (generate multiple functions at a time) and multiple functions (select one or more functions). Java/REST/Python APIs are also supported for the first time with extended data types📷
- Read More: Blog
- How well to other function-calling models perform: Berkeley Function Calling Leaderboard
- Play with the model online: Gorilla OpenFunctions-v2 Web Demo
- Check out the project: GitHub Code
- Model (6.91B) on HuggingFace 🤗: gorilla-llm/gorilla-openfunctions-v2
Benchmarking LLMs on function calling capabilities
🏆 Berkeley Function-Calling Leaderboard (BFCL) 📊 aims to provide a thorough study of the function-calling capability of different LLMs. It consists of 2k 📝 question-function-answer pairs with multiple languages (🐍 Python, ☕ Java, 🟨 JavaScript, 🌐 REST API), diverse application domains, and complex use cases (multiple and parallel function calls). We also investigate function relevance detection 🕵️♂️, to determine how the model will react when the provided function is not suitable to answer the user's question.
- Read More: Blog
- Live Leaderboard: Website
- BFCL Evaluation Dataset: HuggingFace Dataset 🤗
- Gradio Demo: HuggingFace Space 🤗
- Reproducibility: Github Code
Better way to do RAG
RAFT: Retriever-Aware FineTuning for domain-specific RAG 🚀 Drawing parallels between LLMs and students in open-book (RAG) 📔 and closed-book exams (SFT) 🧠, we present a better recipe for fine-tuning a base LLM for RAG-focused challenges. Discover how RAFT prepares LLMs to excel with a specific document set, mirroring students' prep for finals! 🎓
- Read More: Blog
- Read More: MSFT-META Blog
- Paper: https://arxiv.org/abs/2403.10131
- Reproducibility: Github Code
Runtime for executing LLM-generated actions
Gorilla Execution Engine (GoEX) is a runtime for LLM-generated actions like code, API calls, and more. Featuring "post-facto validation" for assessing LLM actions after execution 🔍 Key to our approach is "undo" 🔄 and "damage confinement" abstractions to manage unintended actions & risks. This paves the way for fully autonomous LLM agents, enhancing interaction between apps & services with human-out-of-loop🚀
- Read More: Blog
- Paper: https://arxiv.org/abs/2404.06921
- Try it out: Web Demo
- Reproducibility: GitHub Code
News
🚒 GoEx: A Runtime for executing LLM generated actions like code & API calls GoEx presents “undo” and “damage confinement” abstractions for mitigating the risk of unintended actions taken in LLM-powered systems. Release blog, Paper.
🎉 Berkeley Function Calling Leaderboard! How do models stack up for function calling? 🎯 Read more in our Release Blog.
🏆 Gorilla OpenFunctions v2 Sets new SoTA for open-source LLMs 💪 On-par with GPT-4 🙌 Supports more languages 👌
🥇 Gorilla OpenFunctions! Drop in replacement! Examples
🚀 Try Gorilla in 60s! No sign-ups, no installs, just colab!
🤩 With Apache 2.0 licensed LLM models, you can use Gorilla commercially without any obligations!
📣 We are excited to hear your feedback and we welcome API contributions as we build this open-source project. Join us on Discord or feel free to email us!
Gorilla for your CLI and Spotlight Search
Gorilla powered CLI
Get started with pip install gorilla-cli
Gorilla Powered Spotlight Search
Gorilla-Spotlight
Signup
Vision
Contact Us
Citation
@article{patil2024gorilla,
title={Gorilla: Large Language Model Connected with Massive APIs},
author={Patil, Shishir G. and Zhang, Tianjun and Wang, Xin and Gonzalez, Joseph E.},
booktitle = {Advances in Neural Information Processing Systems},
year={2024},
}