Code AutoComplete
code-autocomplete, a code completion plugin for Python.
code-autocomplete实现了Python代码行粒度和块粒度自动补全功能。
Guide
Feature
Demo
http://42.193.145.218/product/short_text_sim/
Install
pip3 install -U code-autocomplete
or
git clone https://github.com/shibing624/code-autocomplete.git
cd code-autocomplete
python3 setup.py install
Usage
Code Completion
开源项目：code-autocomplete，可支持GPT2模型，通过如下命令调用：
from autocomplete.gpt2 import Infer
m = Infer(model_name="gpt2", model_dir="shibing624/code-autocomplete-gpt2-base", use_cuda=False)
i = m.predict('import torch.nn as')
print(i)
当然，你也可使用官方的huggingface/transformers调用：
Please use 'GPT2' related functions to load this model!
import os
import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = GPT2Tokenizer.from_pretrained("shibing624/code-autocomplete-gpt2-base")
model = GPT2LMHeadModel.from_pretrained("shibing624/code-autocomplete-gpt2-base")
model.to(device)
prompts = [
"""from torch import nn
class LSTM(Module):
def __init__(self, *,
n_tokens: int,
embedding_size: int,
hidden_size: int,
n_layers: int):""",
"""import numpy as np
import torch
import torch.nn as""",
"import java.util.ArrayList",
"def factorial(n):",
]
for prompt in prompts:
input_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors='pt').to(device)
outputs = model.generate(input_ids=input_ids,
max_length=64 + len(prompt),
temperature=1.0,
top_k=50,
top_p=0.95,
repetition_penalty=1.0,
do_sample=True,
num_return_sequences=1,
length_penalty=2.0,
early_stopping=True)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded)
print("=" * 20)
Contact
- Issue(建议)：
- 邮件我：xuming: [email protected]
- 微信我： 加我微信号：xuming624, 备注：个人名称-公司-NLP 进NLP交流群。
Citation
如果你在研究中使用了code-autocomplete，请按如下格式引用：
@misc{code-autocomplete,
author = {Xu Ming},
title = {code-autocomplete: Code AutoComplete with GPT model},
year = {2022},
publisher = {GitHub},
journal = {GitHub repository},
url = {https://github.com/shibing624/code-autocomplete},
}
License
授权协议为 The Apache License 2.0，可免费用做商业用途。请在产品说明中附加code-autocomplete的链接和授权协议。
Contribute
项目代码还很粗糙，如果大家对代码有所改进，欢迎提交回本项目，在提交之前，注意以下两点：
- 在
tests添加相应的单元测试 - 使用
python setup.py test来运行所有单元测试，确保所有单测都是通过的
之后即可提交PR。
32 Nov 9, 2021
564 Jan 8, 2023
91 Sep 23, 2022
3 Dec 5, 2022
1 Dec 6, 2021
0 Oct 25, 2022
101 Dec 26, 2022
423 Jan 1, 2023
27 Dec 14, 2022
57 Dec 16, 2022
1 Nov 08, 2021
121 Jan 05, 2023
829 Jan 07, 2023
1 Dec 11, 2021
483 Jan 04, 2023
4.8k Dec 30, 2022
2 Apr 05, 2022
544 Jan 09, 2023
2 Nov 13, 2021
44 Dec 30, 2022
193 Dec 30, 2022
133 Sep 20, 2022
9 Sep 13, 2021
5 Oct 24, 2022
47 Jul 26, 2022
14 Dec 12, 2022
138 Dec 30, 2022
3 Nov 27, 2022
775 Jan 08, 2023