Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- semeru/code-code-CodeCompletion-TokenLevel-Python
|
4 |
+
metrics:
|
5 |
+
- perplexity
|
6 |
+
base_model:
|
7 |
+
- openai-community/gpt2
|
8 |
+
---
|
9 |
+
|
10 |
+
# Python Code Completion Model (GPT-2)
|
11 |
+
|
12 |
+
This project contains a web-based interface for a Python code completion model developed using HuggingFace. The model is based on GPT-2 and trained on the semeru/code-code-CodeCompletion-TokenLevel-Python dataset. Users can interact with the model via a Streamlit web interface.
|
13 |
+
|
14 |
+
## Project Overview
|
15 |
+
|
16 |
+
This project aims to develop a model for automatic Python code completion. The GPT-2 model used here has been optimized to understand and complete Python code. The model analyzes the code written by the user and suggests relevant completions.
|
17 |
+
|
18 |
+
## Features
|
19 |
+
|
20 |
+
- Model: GPT-2 based, Python code completion
|
21 |
+
- Dataset: semeru/code-code-CodeCompletion-TokenLevel-Python
|
22 |
+
- Web Interface: Streamlit
|
23 |
+
- Platform: HuggingFace
|
24 |
+
- Code Completion: Automatic Python code suggestions
|
25 |
+
|
26 |
+
## Installation
|
27 |
+
|
28 |
+
### 1.Clone the repository:
|
29 |
+
|
30 |
+
git clone https://github.com/your_username/code-completion-model.git
|
31 |
+
cd code-completion-model
|
32 |
+
|
33 |
+
### 2.Install the required dependencies:
|
34 |
+
|
35 |
+
pip install -r requirements.txt
|
36 |
+
|
37 |
+
### 3.To upload your model to HuggingFace, you can use transformers-cli:
|
38 |
+
|
39 |
+
transformers-cli login
|
40 |
+
transformers-cli upload ./path_to_your_model
|
41 |
+
|
42 |
+
### 4.Start the Streamlit app:
|
43 |
+
|
44 |
+
streamlit run app.py
|
45 |
+
|