codegeex glm chatglm thudm

<p align="center"> 🏠 <a href="https://codegeex.cn" target="_blank">Homepage</a>｜💻 <a href="https://github.com/THUDM/CodeGeeX2" target="_blank">GitHub</a>｜🛠 Tools <a href="https://marketplace.visualstudio.com/items?itemName=aminer.codegeex" target="_blank">VS Code</a>, <a href="https://plugins.jetbrains.com/plugin/20587-codegeex" target="_blank">Jetbrains</a>｜🤗 <a href="https://huggingface.co/THUDM/codegeex2-6b" target="_blank">HF Repo</a>｜📄 <a href="https://arxiv.org/abs/2303.17568" target="_blank">Paper</a> </p>

<p align="center"> 👋 Join our <a href="https://discord.gg/8gjHdkmAN6" target="_blank">Discord</a>, <a href="https://join.slack.com/t/codegeexworkspace/shared_invite/zt-1s118ffrp-mpKKhQD0tKBmzNZVCyEZLw" target="_blank">Slack</a>, <a href="https://t.me/+IipIayJ32B1jOTg1" target="_blank">Telegram</a>, <a href="https://github.com/THUDM/CodeGeeX2/blob/main/resources/wechat.md"target="_blank">WeChat</a> </p>

INT4量化版本｜INT4 quantized version codegeex2-6b-int4

CodeGeeX2: 更强大的多语言代码生成模型

A More Powerful Multilingual Code Generation Model

CodeGeeX2 是多语言代码生成模型 CodeGeeX (KDD’23) 的第二代模型。CodeGeeX2 基于 ChatGLM2 架构加入代码预训练实现，得益于 ChatGLM2 的更优性能，CodeGeeX2 在多项指标上取得性能提升（+107% > CodeGeeX；仅60亿参数即超过150亿参数的 StarCoder-15B 近10%），更多特性包括：

CodeGeeX2 is the second-generation model of the multilingual code generation model CodeGeeX (KDD’23), which is implemented based on the ChatGLM2 architecture trained on more code data. Due to the advantage of ChatGLM2, CodeGeeX2 has been comprehensively improved in coding capability (+107% > CodeGeeX; with only 6B parameters, surpassing larger StarCoder-15B for some tasks). It has the following features:

软件依赖 ｜ Dependency

pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2html sentencepiece accelerate

快速开始 ｜ Get Started

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/codegeex2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/codegeex2-6b", trust_remote_code=True, device='cuda')
model = model.eval()

# remember adding a language tag for better performance
prompt = "# language: Python\n# write a bubble sort function\n"
inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_length=256, top_k=1)
response = tokenizer.decode(outputs[0])

>>> print(response)
# language: Python
# write a bubble sort function


def bubble_sort(list):
    for i in range(len(list) - 1):
        for j in range(len(list) - 1):
            if list[j] > list[j + 1]:
                list[j], list[j + 1] = list[j + 1], list[j]
    return list


print(bubble_sort([5, 2, 1, 8, 4]))

关于更多的使用说明，请参考 CodeGeeX2 的 Github Repo。

For more information, please refer to CodeGeeX2's Github Repo.

协议 ｜ License

本仓库的代码依照 Apache-2.0 协议开源，模型的权重的使用则需要遵循 Model License。

The code in this repository is open source under the Apache-2.0 license. The model weights are licensed under the Model License.

引用 ｜ Citation

如果觉得我们的工作有帮助，欢迎引用以下论文：

If you find our work helpful, please feel free to cite the following paper:

@inproceedings{zheng2023codegeex,
      title={CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X}, 
      author={Qinkai Zheng and Xiao Xia and Xu Zou and Yuxiao Dong and Shan Wang and Yufei Xue and Zihan Wang and Lei Shen and Andi Wang and Yang Li and Teng Su and Zhilin Yang and Jie Tang},
      booktitle={KDD},
      year={2023}
}