|
# CodeGeeX4: 开源多语言代码生成模型 |
|
|
|
[CodeGeeX4 GitHub](https://github.com/THUDM/CodeGeeX4) |
|
|
|
我们推出了 CodeGeeX4-ALL-9B,这是最新的 CodeGeeX4 系列模型的开源版本。该模型是在 [GLM-4-9B](https://github.com/THUDM/GLM-4) 基础上持续训练的多语言代码生成模型,显著提升了代码生成能力。使用单个 CodeGeeX4-ALL-9B 模型,可以支持代码补全与生成、代码解释、联网搜索、函数调用、仓库级代码问答等多种功能,覆盖了软件开发的各个场景。CodeGeeX4-ALL-9B 在 [BigCodeBench](https://huggingface.co/datasets/bigcode/bigcodebench) 和 [NaturalCodeBench](https://github.com/THUDM/NaturalCodeBench) 等公开基准测试中取得了极具竞争力的表现。它是目前参数量少于 100 亿的最强代码生成模型,甚至超越了更大的通用模型,在推理速度和模型性能方面达到了最佳平衡。 |
|
|
|
|
|
## 快速开始 |
|
|
|
请使用 `4.39.0<=transformers<=4.40.2` 部署: |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
tokenizer = AutoTokenizer.from_pretrained("THUDM/codegeex4-all-9b", trust_remote_code=True) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
"THUDM/codegeex4-all-9b", |
|
torch_dtype=torch.bfloat16, |
|
low_cpu_mem_usage=True, |
|
trust_remote_code=True |
|
).to(device).eval() |
|
inputs = tokenizer.apply_chat_template([{"role": "user", "content": "write a quick sort"}], add_generation_prompt=True, tokenize=True, return_tensors="pt", return_dict=True).to(device) |
|
with torch.no_grad(): |
|
outputs = model.generate(**inputs) |
|
outputs = outputs[:, inputs['input_ids'].shape[1]:] |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
## 评测指标 |
|
|
|
| **模型** | **序列长度** | **HumanEval** | **MBPP** | **NCB** | **LCB** | **HumanEvalFIM** | **CRUXEval-O** | |
|
|-----------------------------|----------------|---------------|----------|---------|---------|------------------|----------------| |
|
| Llama3-70B-intruct | 8K | 77.4 | 82.3 | 37.0 | 27.4 | - | - | |
|
| DeepSeek Coder 33B Instruct | 16K | 81.1 | 80.4 | 39.3 | 29.3 | 78.2 | 49.9 | |
|
| Codestral-22B | 32K | 81.1 | 78.2 | 46.0 | 35.3 | 91.6 | 51.3 | |
|
| CodeGeeX4-All-9B | 128K | 82.3 | 75.7 | 40.4 | 28.5 | 85.0 | 47.1 | |
|
|
|
## License |
|
|
|
CodeGeeX4-ALL-9B 模型的权重的使用则需要遵循 [License](./LICENSE). |
|
|
|
|
|
## 引用 |
|
|
|
如果您觉得我们的工作对您有帮助,欢迎引用以下论文: |
|
|
|
``` |
|
@inproceedings{zheng2023codegeex, |
|
title={CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking 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={Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining}, |
|
pages={5673--5684}, |
|
year={2023} |
|
} |
|
``` |
|
|