Canstralian commited on
Commit
4a0e67c
·
verified ·
1 Parent(s): cda2117

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -2
README.md CHANGED
@@ -4,10 +4,53 @@ emoji: 🦀
4
  colorFrom: red
5
  colorTo: gray
6
  sdk: gradio
7
- sdk_version: 4.43.0
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
  ---
12
 
13
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  colorFrom: red
5
  colorTo: gray
6
  sdk: gradio
7
+ sdk_version: 5.9.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
  ---
12
 
13
+ # SQL Generation 🦀
14
+
15
+ Welcome to the **SQL Generation** Gradio application! This tool leverages advanced machine learning models to assist in generating SQL queries based on natural language inputs. Whether you're a developer, data analyst, or just curious about SQL, this app aims to simplify the process of crafting SQL queries.
16
+
17
+ ## Features
18
+
19
+ - **Natural Language to SQL**: Convert plain English descriptions into SQL queries.
20
+ - **Multiple Datasets**: Trained on diverse datasets to handle various SQL generation tasks.
21
+ - **User-Friendly Interface**: Built with Gradio for an intuitive and interactive experience.
22
+
23
+ ## Installation
24
+
25
+ To run this application locally, ensure you have Python 3.10 or higher installed. Then, install the required dependencies:
26
+
27
+ ```bash
28
+ pip install gradio transformers datasets
29
+ ```
30
+ ## Usage
31
+ After installing the dependencies, you can start the application by running:
32
+
33
+ ```bash
34
+ python app.py
35
+ ```
36
+ This will launch a local server. Open your browser and navigate to http://127.0.0.1:7860 to access the interface.
37
+
38
+ ### Datasets Used
39
+ The model has been trained on the following datasets:
40
+ - b-mc2/sql-create-context: Provides context for SQL query generation.
41
+ - TuneIt/o1-python: Offers examples of Python code snippets.
42
+ - HuggingFaceFW/fineweb-2: Includes various language models for fine-tuning.
43
+ - sentence-transformers/embedding-training-data: Supplies data for training sentence embeddings.
44
+
45
+ ## Model
46
+ The application utilizes the distilbert-base-uncased model from Hugging Face, known for its efficiency and performance in natural language processing tasks.
47
+
48
+ ## License
49
+ This project is licensed under the MIT License.
50
+
51
+ ## Acknowledgments
52
+ - **Gradio** for providing an easy-to-use interface for machine learning models.
53
+ - **Hugging Face** for hosting the pre-trained models and datasets.
54
+ - **Datasets** for offering a wide range of datasets for training and evaluation.
55
+
56
+ For more information, refer to the **Gradio** documentation.