zai-org/codegeex

★ 8,781PythonAudience · developerComplexity · 4/5Setup · hard

Mindmap

mindmap
  root((CodeGeeX))
    What it does
      Code completion
      Code translation
      Multi-language support
    How to Use
      VS Code extension
      JetBrains plugin
      Local model weights
    Model Details
      13B parameters
      20 plus languages
      KDD 2023 paper
    Benchmark
      HumanEval-X
      820 coding problems
      5 languages tested
    Requirements
      GPU with 15GB VRAM
      26GB model download

mindmap root((CodeGeeX)) What it does Code completion Code translation Multi-language support How to Use VS Code extension JetBrains plugin Local model weights Model Details 13B parameters 20 plus languages KDD 2023 paper Benchmark HumanEval-X 820 coding problems 5 languages tested Requirements GPU with 15GB VRAM 26GB model download

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Install the free VS Code or JetBrains extension to get AI-powered code completion inside your existing editor without any local setup.

USE CASE 2

Translate a function written in Python into Go, Java, or another language using the model's built-in code translation feature.

USE CASE 3

Run CodeGeeX locally on a GPU server after downloading the model weights to get private, self-hosted code generation.

USE CASE 4

Use the HumanEval-X benchmark to evaluate and compare code generation models across Python, Java, Go, C++, and JavaScript.

Tech stack

PythonCUDA

Getting it running

Difficulty · hard Time to first run · 5min

The VS Code and JetBrains extensions work immediately with no local setup, running the model weights locally requires an NVIDIA or Ascend GPU with at least 15GB VRAM and a 26GB download.

In plain English

CodeGeeX is an AI model trained to write and translate code. It has 13 billion parameters and was trained on code written in more than 20 programming languages, including Python, C++, Java, JavaScript, and Go. The model can complete code, generate functions from descriptions, and convert a piece of code written in one language into another language. The project was developed by researchers and published at the KDD 2023 conference. It was trained on Huawei's Ascend AI processors but can also run on NVIDIA GPUs. The model weights are available for download after submitting a request through the project's website, and the download is around 26 gigabytes. For everyday use, CodeGeeX is available as a free extension for VS Code and JetBrains IDEs such as IntelliJ IDEA and PyCharm. The extension provides code completion, code explanation, and code summarization directly inside the editor. This means you can install it into the tool you already use to write code and interact with the model without running anything separately. The repository also includes a benchmark called HumanEval-X, which is a set of 820 hand-written coding problems across five programming languages. Each problem includes tests and a reference solution. The benchmark was created to give researchers a consistent way to measure how well code generation models perform across different languages, not just Python. It is available on the Hugging Face dataset platform. Model weights can be run with reduced GPU memory requirements through quantization, which the repository describes as dropping from 27GB to 15GB of GPU RAM. A newer version of the model, CodeGeeX2, is also mentioned in the README as a separate release with support for over 100 languages.

Copy-paste prompts

Prompt 1

Install the CodeGeeX extension in VS Code and help me write a Python function that reads a CSV file and returns the top 5 rows sorted by a specified column. Show me how to trigger the completion.

Prompt 2

Use CodeGeeX to translate this Python snippet into Go: 'import pandas as pd, df = pd.read_csv("data.csv"), print(df.head())'. Give me the idiomatic Go equivalent.

Prompt 3

I want to run CodeGeeX locally on my GPU server. Walk me through requesting the model weights, setting up the Python environment, and running inference on a test prompt.

Prompt 4

What is HumanEval-X and how do I use it to benchmark a code generation model across Python, Java, and C++? Show me the steps to run the evaluation.

Prompt 5

CodeGeeX has a CodeGeeX2 version mentioned as a separate release. What are the key differences and when should I use CodeGeeX2 instead of the original?

Open on GitHub → Explain another repo

← zai-org on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.