first commit

README.md

@@ -1,5 +1,5 @@
 ---
-title: Zstc
+title: zstc
 emoji: 👁
 colorFrom: green
 colorTo: red
@@ -10,4 +10,53 @@ pinned: false
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Zero-Shot Text Classification with BART
+
+This project demonstrates a web application built with Gradio that utilizes the `facebook/bart-large-mnli` model for zero-shot text classification. Users can input text and specify candidate labels to see how the model classifies the input without having been directly trained on those labels.
+
+## Features
+
+- **Zero-Shot Classification:** Classify text into user-specified categories without direct training on those categories.
+- **User-Friendly Interface:** Easy-to-use web interface built with Gradio.
+- **Multi-Label Support:** Option for multi-label classification, allowing a single piece of text to belong to multiple categories.
+
+## Installation
+
+To run this project, you will need Python and pip. First, clone this repository and navigate to the project directory. Then, install the required dependencies:
+
+```bash
+pip install gradio transformers
+```
+
+## Usage
+
+To start the application, run the Python script:
+
+```bash
+python app.py
+```
+
+Navigate to the URL provided by Gradio in your terminal to access the web interface.
+
+## Examples
+
+The application includes predefined examples that demonstrate how to use the interface:
+
+- "The market has been incredibly volatile this year, with tech stocks leading the charge." with labels "finance, technology, sports, education"
+- "LeBron James scores 30 points to lead the Lakers to a Game 7 victory over the Celtics." with labels "sports, technology, finance, entertainment"
+- And more...
+
+## Customization
+
+You can customize the candidate labels and select whether the classification should be multi-label directly in the interface.
+
+## Technology
+
+This project is built using the following technologies:
+
+- **Gradio:** An open-source library to build ML-powered web apps.
+- **Transformers:** A state-of-the-art natural language processing library.
+
+## Author
+
+- [Lucian BLETAN](https://github.com/exaluc)

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from transformers import pipeline
+
+# Initialize the zero-shot classification pipeline with the BART model
+classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+def classify_text(sequence, candidate_labels, multi_label):
+    # Split candidate labels entered by the user
+    labels = [label.strip() for label in candidate_labels.split(',')]
+    # Perform classification
+    results = classifier(sequence, labels, multi_label=multi_label)
+    # Format the results
+    formatted_results = {label: score for label, score in zip(results['labels'], results['scores'])}
+    return formatted_results
+
+# Examples for the interface
+examples = [
+    ["The market has been incredibly volatile this year, with tech stocks leading the charge.", "finance, technology, sports, education", False],
+    ["LeBron James scores 30 points to lead the Lakers to a Game 7 victory over the Celtics.", "sports, technology, finance, entertainment", False],
+    ["Tesla's new battery technology could revolutionize the electric vehicle industry.", "technology, finance, environment, education", False],
+    ["The local school district has announced a new STEM initiative to better prepare students for careers in technology.", "education, technology, politics, finance", False],
+]
+
+# Define Gradio interface components
+iface = gr.Interface(fn=classify_text,
+                     inputs=[gr.Textbox(label="Text to classify"),
+                             gr.Textbox(label="Candidate labels (comma-separated)"),
+                             gr.Checkbox(label="Multi-label classification", value=False)],
+                     outputs=gr.JSON(label="Classification Results"),
+                     title="Zero-Shot Text Classification with BART",
+                     description="This model uses 'bart-large-mnli' for zero-shot text classification. Enter text to classify, provide candidate labels separated by commas, and select whether it's multi-label classification.",
+                     examples=examples,
+                     css="footer{display:none !important}",
+                     allow_flagging="never")
+
+if __name__ == "__main__":
+    iface.launch()