A
AutoCoder
bin123apple/AutoCoder
We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
★848stars
Python
Apache-2.0
Updated: 1w ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Python, focusing on code-generation and code-interpreter
Who made it?Maintained by bin123apple team, 848⭐ on GitHub, #1287 out of 3201 in Models
Why does it exist?The bin123apple team recognized that existing code-generation tools in Models were hard to use. AutoCoder was designed to make code-interpreter more accessible.
What can it do?Key use cases: humaneval, llm, nlp
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/bin123apple/AutoCoder | 官网 https://arxiv.org/abs/2405.14906
🔗 github.com/bin123apple/AutoCoder | 官网 https://arxiv.org/abs/2405.14906
Topics
code-generationcode-interpreterhumanevalllmnlpnlp-machine-learningtext-generation