GraphCanon
Home/Model Training/CodeGeeX
CodeGeeX logo

CodeGeeX

Enrichment pending
zai-org/CodeGeeX

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

GitHub Website

GraphCanon updated today · GitHub synced today

8.8k
Stars
689
Forks
188
Open issues
85
Watchers
1y
Last push
Python Apache-2.0Created Sep 17, 2022

Trust & integrity

Full report
Maintenance
Dormant (697d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Organization account
As of today · Source: github_public_v1
Security (OSV)
85 low (85 low)
As of today · Source: osv@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

Capability facts

Languages
python

Source: github.language · Jul 11, 2026

Categories

Model TrainingDeveloper Tools

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

Python 3.7+ / CUDA 11+ / PyTorch 1.10+ / DeepSpeed 0.6+ are required. Install ``codegeex``
Source link

Tags

pretrained modelspythontoolscode-generation

README

Getting Started

CodeGeeX is initially implemented in Mindspore and trained Ascend 910 AI Processors. We provide a torch-compatible version based on Megatron-LM to facilitate usage on GPU platforms.

Installation

Python 3.7+ / CUDA 11+ / PyTorch 1.10+ / DeepSpeed 0.6+ are required. Install codegeex package via:

git clone git@github.com:THUDM/CodeGeeX.git
cd CodeGeeX
pip install -e .

Or use CodeGeeX docker to quickly set up the environment (with nvidia-docker installed):

docker pull codegeex/codegeex:latest

---

## License

Our code is licensed under the [Apache-2.0 license](LICENSE).
Our model is licensed under the [license](MODEL_LICENSE).