Code Autocomplete Distilgpt2 Python

🚀 GPT2 for Code AutoComplete Model

A code completion plugin for Python that leverages GPT2 to automatically complete lines and blocks of code.

🚀 Quick Start

The open - source repository code - autocomplete supports the GPT2 model. Here's how to use it:

from autocomplete.gpt2_coder import GPT2Coder

m = GPT2Coder("shibing624/code-autocomplete-distilgpt2-python")
print(m.generate('import torch.nn as')[0])

You can also use huggingface/transformers.

⚠️ Important Note

Please use 'GPT2' related functions to load this model!

import os
from transformers import GPT2Tokenizer, GPT2LMHeadModel

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

tokenizer = GPT2Tokenizer.from_pretrained("shibing624/code-autocomplete-distilgpt2-python")
model = GPT2LMHeadModel.from_pretrained("shibing624/code-autocomplete-distilgpt2-python")

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')
    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)

Output Example

from torch import nn
    class LSTM(Module):
        def __init__(self, *,
                     n_tokens: int,
                     embedding_size: int,
                     hidden_size: int,
                     n_layers: int):
            self.embedding_size = embedding_size
====================
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F

Model Files

code-autocomplete-distilgpt2-python
├── config.json
├── merges.txt
├── pytorch_model.bin
├── special_tokens_map.json
├── tokenizer_config.json
└── vocab.json

📚 Documentation

Training Data

Pytorch_awesome projects source code

You can download code - autocomplete and run the following commands:

cd autocomplete
python create_dataset.py

If you want to train the code - autocomplete GPT2 model, refer to https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2_coder.py

About GPT2

You can test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large

The GPT2 model is a pretrained model on the English language using a causal language modeling (CLM) objective. It was introduced in this paper and first released at this page.

Disclaimer: The team releasing GPT - 2 also wrote a model card for their model. Content from this model card has been written by the Hugging Face team to complete the information they provided and give specific examples of bias.

📄 License

This project is licensed under the Apache - 2.0 license.

📖 Citation

@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},
}