Upload folder using huggingface_hub

README.md

@@ -1,12 +1,14 @@
----
-title: Python Docstring Generator
-emoji: 🏆
-colorFrom: green
-colorTo: red
-sdk: gradio
-sdk_version: 6.6.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Python Docstring Generator
+emoji: 📝
+colorFrom: blue
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.0.0
+app_file: app.py
+pinned: false
+---
+
+# Python Docstring Generator
+
+Paste a Python code snippet to get a short docstring summary (T5-based). By [syeedalireza](https://huggingface.co/syeedalireza).

app.py

@@ -0,0 +1,26 @@
+"""
+Gradio Space: Python docstring generation. Run: gradio app.py
+"""
+import gradio as gr
+from inference import generate_docstring
+
+
+def summarize_code(code: str) -> str:
+    if not code or not code.strip():
+        return "Paste a Python code snippet above."
+    return generate_docstring(code, model_name="t5-small", max_length=128, num_beams=4)
+
+
+demo = gr.Interface(
+    fn=summarize_code,
+    inputs=gr.Textbox(
+        label="Python code",
+        placeholder="def add(a, b):\n    return a + b",
+        lines=8,
+    ),
+    outputs=gr.Textbox(label="Generated docstring"),
+    title="Python Docstring Generator",
+    description="Paste a Python function or snippet to get a short docstring summary.",
+)
+
+demo.launch()

inference.py

@@ -0,0 +1,23 @@
+"""
+Inference for docstring generation. Uses T5.
+"""
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+import torch
+
+
+def generate_docstring(
+    code: str,
+    model_name: str = "t5-small",
+    max_length: int = 128,
+    num_beams: int = 4,
+    device: str = None,
+) -> str:
+    if device is None:
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name).to(device)
+    input_text = "summarize: " + code
+    inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=512).to(device)
+    with torch.no_grad():
+        out = model.generate(**inputs, max_length=max_length, num_beams=num_beams, early_stopping=True)
+    return tokenizer.decode(out[0], skip_special_tokens=True)

requirements.txt

@@ -0,0 +1,3 @@
+torch>=2.0.0
+transformers>=4.30.0
+gradio>=4.0.0