Create app.py

app.py

@@ -0,0 +1,58 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
+
+MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+def chat(user_input, history):
+    messages = []
+
+    for h in history:
+        messages.append({"role": "user", "content": h[0]})
+        messages.append({"role": "assistant", "content": h[1]})
+
+    messages.append({"role": "user", "content": user_input})
+
+    prompt = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9
+    )
+
+    response = tokenizer.decode(
+        outputs[0][inputs["input_ids"].shape[-1]:],
+        skip_special_tokens=True
+    )
+
+    history.append((user_input, response))
+    return history, ""
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 Qwen Chatbot")
+
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Your message")
+    clear = gr.Button("Clear")
+
+    msg.submit(chat, [msg, chatbot], [chatbot, msg])
+    clear.click(lambda: [], None, chatbot)
+
+demo.launch()