Create app.py

app.py

@@ -0,0 +1,22 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+
+model_name = "Qwen/Qwen3.5-35B-A3B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+def chat(message, history):
+    messages = []
+    for user, assistant in history:
+        messages.append({"role": "user", "content": user})
+        messages.append({"role": "assistant", "content": assistant})
+    messages.append({"role": "user", "content": message})
+
+    text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = tokenizer([text], return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=512)
+    output = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
+    return output
+
+gr.ChatInterface(chat).launch(server_name="0.0.0.0", server_port=7860)