awesome-large-action-model  by tjtanaa

Collection of Large Action Models for task automation

created 1 year ago
267 stars

Top 96.7% on sourcepulse

GitHubView on GitHub
Project Summary

This repository curates a list of open-source Large Action Models (LAMs) designed to assist users in accomplishing tasks. It targets researchers and developers interested in LLMs capable of interacting with external tools and environments, offering a centralized resource for cutting-edge advancements in this domain.

How It Works

The collection highlights models that bridge the gap between LLMs and real-world actions, often by enabling them to understand and utilize a vast array of APIs or graphical user interfaces. This approach allows LLMs to move beyond text generation towards task execution and automation.

Highlighted Details

  • CogAgent: A Visual Language Model for GUI Agents.
  • Gorilla: Large Language Model Connected with Massive APIs.
  • ToolLLM: Facilitating LLMs to Master 16000+ Real-world APIs.
  • MetaTool Benchmark: Evaluating tool selection for LLMs.
  • T-Eval: Step-by-step evaluation of tool utilization capabilities.

Maintenance & Community

This is a curated list, with contributions likely driven by the research community. Specific maintainer details or community links are not provided in the README.

Licensing & Compatibility

The licensing for individual models listed varies. Users must consult the specific licenses of each project (e.g., CogAgent, Gorilla, ToolLLM) for compatibility and usage restrictions.

Limitations & Caveats

This repository is a collection of links and resources, not a runnable project itself. Users must individually set up and evaluate each listed Large Action Model.

Health Check
Last commit

1 year ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
5 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Victor Taelin Victor Taelin(Author of Bend, Kind, HVM), and
4 more.

AgentBench by THUDM

0.5%
3k
Benchmark for evaluating LLMs as agents across diverse environments
created 2 years ago
updated 6 months ago
Starred by Ying Sheng Ying Sheng(Author of SGLang), Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), and
2 more.

ToolBench by OpenBMB

0.2%
5k
Open platform for LLM tool learning (ICLR'24 spotlight)
created 2 years ago
updated 2 months ago
Feedback? Help us improve.