Create app.py

app.py

@@ -0,0 +1,62 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+MODEL_NAME = "Qwen/Qwen2.5-Coder-1.5B-Instruct"
+
+print("Loading model... (this may take a minute)")
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float32,
+    device_map="cpu"
+)
+
+print("Model loaded!")
+
+
+def generate_code(prompt):
+    if not prompt.strip():
+        return "Please enter a prompt."
+
+    inputs = tokenizer(prompt, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=512,
+            temperature=0.2,
+            do_sample=True
+        )
+
+    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Remove the original prompt from output
+    if result.startswith(prompt):
+        result = result[len(prompt):]
+
+    return result.strip()
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 💻 Local AI Code Generator (CPU)")
+    gr.Markdown("Runs fully locally on Hugging Face Space 🚀")
+
+    prompt = gr.Textbox(
+        label="Your Prompt",
+        placeholder="e.g. Create a Python calculator",
+        lines=4
+    )
+
+    btn = gr.Button("Generate")
+
+    output = gr.Code(
+        label="Generated Code",
+        language="python"
+    )
+
+    btn.click(generate_code, inputs=prompt, outputs=output)
+
+demo.launch()