InternLM/Agent-FLAN

[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

34
/ 100
Emerging

This project helps AI developers enhance the reasoning and tool-use capabilities of open-source large language models (LLMs). It takes an existing LLM and specialized agent-tuning datasets, then outputs a refined LLM that performs better in complex agent tasks, such as using external tools or performing multi-step reasoning. AI engineers or researchers building agentic LLM applications would use this.

359 stars. No commits in the last 6 months.

Use this if you are an AI developer looking to improve an open-source LLM's ability to act as an autonomous agent and effectively use tools, while minimizing issues like hallucinations.

Not ideal if you are an end-user without deep technical expertise in LLM fine-tuning or if you primarily work with proprietary, API-based LLMs rather than open-source models.

AI model tuning LLM agent development Natural Language Processing tool utilization AI research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

359

Forks

10

Language

License

Apache-2.0

Category

llm-fine-tuning

Last pushed

Mar 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/InternLM/Agent-FLAN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.