|
--- |
|
license: other |
|
license_name: codegeex4 |
|
license_link: https://huggingface.co/THUDM/codegeex4-all-9b/blob/main/LICENSE |
|
language: |
|
- zh |
|
- en |
|
tags: |
|
- glm |
|
- codegeex |
|
- thudm |
|
inference: false |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# CodeGeeX4: Open Multilingual Code Generation Model |
|
|
|
[中文](./README_zh.md) |
|
|
|
We introduce CodeGeeX4-ALL-9B, the open-source version of the latest CodeGeeX4 model series. It is a multilingual code generation model continually trained on the [GLM-4-9B](https://github.com/THUDM/GLM-4), significantly enhancing its code generation capabilities. Using a single CodeGeeX4-ALL-9B model, it can support comprehensive functions such as code completion and generation, code interpreter, web search, function call, repository-level code Q&A, covering various scenarios of software development. CodeGeeX4-ALL-9B has achieved highly competitive performance on public benchmarks, such as [BigCodeBench](https://huggingface.co/datasets/bigcode/bigcodebench) and [NaturalCodeBench](https://github.com/THUDM/NaturalCodeBench). It is currently the most powerful code generation model with less than 10B parameters, even surpassing much larger general-purpose models, achieving the best balance in terms of inference speed and model performance. |
|
|
|
## Get Started |
|
|
|
Use `4.39.0<=transformers<=4.40.2` to quickly launch [codegeex4-all-9b](https://huggingface.co/THUDM/codegeex2-6b)： |
|
|
|
```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)) |
|
``` |
|
|
|
|
|
## License |
|
|
|
The model weights are licensed under the [Model License](MODEL_LICENSE). |
|
|
|
|
|
## Citation |
|
|
|
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} |
|
} |
|
``` |
