Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

AgentLM-7B

Model basics

Reasoning traces

Not supported

Context length

8K tokens

Max output length

No data

Model type

聊天大模型

Release date

2023-10-19

Model file size

13.42

MoE architecture

Total params / Active params

70.0B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

AgentLM-7B

Open source & experience

Code license

Llama 2 Community License Agreement

Weights license

Llama 2 Community License Agreement- 免费商用授权

GitHub repo

https://github.com/THUDM/AgentTuning

Hugging Face

https://huggingface.co/THUDM/agentlm-7b

Live demo

No live demo

AgentLM-7B

Official resources

Paper

AgentTuning: Enabling Generalized Agent Abilities for LLMs

DataLearnerAI blog

No blog post yet

AgentLM-7B

API details

API speed

No data

No public API pricing yet.

AgentLM-7B

Benchmark Results

No benchmark data to show.

AgentLM-7B

Publisher

智谱AI

View publisher details

AgentLM-7B

Model Overview

AgentLM-7B是清华大学和智谱AI联合开源的一个针对AI Agent任务微调的大语言模型，其基础模型是LLaMA2-7B。使用了AgentInstruct数据集，针对AI Agent任务微调。这个版本是70亿参数版本。

具体参考： https://www.datalearner.com/blog/1051698150066829

Foundation model

LLaMA2

View details

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送