Gradio Python coder using the fine-tuned Qwen2.5-0.5B LoRA

README.md

@@ -1,12 +1,29 @@
 ---
 title: PyCoder
-emoji: 🦀
+emoji: 🐍
 colorFrom: pink
 colorTo: green
-sdk: static
+sdk: gradio
+sdk_version: 5.49.1
+app_file: app.py
 pinned: false
 license: mit
-short_description: Lightweight coding chatbot powered by Qwen2.5-0.5B-Instruc
+short_description: Lightweight Python coding chatbot (Qwen2.5-0.5B + LoRA)
+models:
+  - Qwen/Qwen2.5-0.5B-Instruct
+  - ali4566544/qwen2.5-0.5b-instruct-python-lora
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# PyCoder
+
+A simple Python coding chatbot built with Gradio. It runs
+[Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) with the
+[ali4566544/qwen2.5-0.5b-instruct-python-lora](https://huggingface.co/ali4566544/qwen2.5-0.5b-instruct-python-lora)
+adapter merged in, on CPU, and streams responses.
+
+Run locally:
+
+```bash
+pip install gradio -r requirements.txt
+python app.py
+```

app.py

@@ -0,0 +1,68 @@
+import threading
+
+import gradio as gr
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+
+BASE_MODEL = "Qwen/Qwen2.5-0.5B-Instruct"
+ADAPTER = "ali4566544/qwen2.5-0.5b-instruct-python-lora"
+# The adapter was trained with this exact system prompt.
+SYSTEM_PROMPT = (
+    "You are a helpful Python coding assistant. Write clear, correct, idiomatic Python, "
+    "explain the code concisely, and point out bugs and how to fix them when asked."
+)
+
+tokenizer = AutoTokenizer.from_pretrained(ADAPTER)
+base = AutoModelForCausalLM.from_pretrained(BASE_MODEL, torch_dtype=torch.float32)
+# Merge LoRA weights into the base model for faster CPU inference.
+model = PeftModel.from_pretrained(base, ADAPTER).merge_and_unload()
+model.eval()
+
+
+def respond(message, history, max_new_tokens, temperature):
+    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
+    messages += [{"role": m["role"], "content": m["content"]} for m in history]
+    messages.append({"role": "user", "content": message})
+
+    inputs = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_tensors="pt", return_dict=True
+    )
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    gen_kwargs = dict(**inputs, streamer=streamer, max_new_tokens=int(max_new_tokens))
+    if temperature > 0:
+        gen_kwargs.update(do_sample=True, temperature=temperature, top_p=0.9)
+    else:
+        gen_kwargs.update(do_sample=False)
+
+    threading.Thread(target=model.generate, kwargs=gen_kwargs).start()
+    output = ""
+    for chunk in streamer:
+        output += chunk
+        yield output
+
+
+demo = gr.ChatInterface(
+    respond,
+    type="messages",
+    title="🐍 PyCoder",
+    description=(
+        "A small Python coding assistant: Qwen2.5-0.5B-Instruct fine-tuned with a "
+        f"[LoRA adapter](https://huggingface.co/{ADAPTER}). It's a 0.5B learning project, "
+        "so always run and test the code it writes."
+    ),
+    additional_inputs=[
+        gr.Slider(64, 1024, value=512, step=32, label="Max new tokens"),
+        gr.Slider(0.0, 1.5, value=0.0, step=0.1, label="Temperature (0 = greedy)"),
+    ],
+    examples=[
+        ["Write a function that removes duplicates from a list while keeping order."],
+        ["How do I read a CSV file with pandas and drop rows with missing values?"],
+        ["Write a minimal FastAPI app with a /health endpoint."],
+        ["Why does this fail? `for i in range(len(xs)): xs.remove(xs[i])`"],
+    ],
+    cache_examples=False,
+)
+
+if __name__ == "__main__":
+    demo.launch()

index.html

@@ -1,19 +0,0 @@
-<!doctype html>
-<html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
-</html>

requirements.txt

@@ -0,0 +1,4 @@
+--extra-index-url https://download.pytorch.org/whl/cpu
+torch
+transformers==4.57.1
+peft==0.17.1

style.css

@@ -1,28 +0,0 @@
-body {
-	padding: 2rem;
-	font-family: -apple-system, BlinkMacSystemFont, "Arial", sans-serif;
-}
-
-h1 {
-	font-size: 16px;
-	margin-top: 0;
-}
-
-p {
-	color: rgb(107, 114, 128);
-	font-size: 15px;
-	margin-bottom: 10px;
-	margin-top: 5px;
-}
-
-.card {
-	max-width: 620px;
-	margin: 0 auto;
-	padding: 16px;
-	border: 1px solid lightgray;
-	border-radius: 16px;
-}
-
-.card p:last-child {
-	margin-bottom: 0;
-}