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

AquilaCode-7B-py

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

编程大模型

Release date

2023-07-24

Model file size

13.3GB

MoE architecture

Total params / Active params

70.0B / N/A

Knowledge cutoff

No data

AquilaCode-7B-py

Open source & experience

Code license

Apache 2.0

Weights license

智源Aquila系列模型许可协议- 免费商用授权

GitHub repo

https://github.com/FlagAI-Open/FlagAI/tree/master/examples/Aquila/Aquila-code

Hugging Face

https://huggingface.co/BAAI/AquilaCode-py

Live demo

No live demo

AquilaCode-7B-py

Official resources

Paper

悟道·天鹰 AquilaCode升级多语言代码生成，多项指标领先，开源可商用

DataLearnerAI blog

No blog post yet

AquilaCode-7B-py

API details

API speed

No data

No public API pricing yet.

AquilaCode-7B-py

Benchmark Results

No benchmark data to show.

AquilaCode-7B-py

Publisher

北京智源人工智能研究院

View publisher details

AquilaCode-7B-py

Model Overview

AquilaCode-py是北京智源人工智能研究院开源的可商用编程大模型，是基于Aquila-7B模型训练得到的。AquilaCode-py是单语言python版。

2023年7月24日，BAAI发布了2个编程大模型，分别是Aquila-multi-7B和Aquila-7B-py。前者是多语言支持版本，支持包括Python/C++/Java/JavaScript/Go等。

Aquila-multi-7B模型的评测效果很好：

Foundation model

Aquila

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