Create app.py

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the model and tokenizer
+model_name = "Qwen/Qwen2.5-Coder-32B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Function to interact with the model
+def chat_with_model(user_input):
+    prompt = user_input
+    messages = [
+        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+        {"role": "user", "content": prompt}
+    ]
+    
+    # Use apply_chat_template to format messages for the model
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    
+    # Tokenize the input and send it to the model
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+    
+    # Generate the response from the model
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=512
+    )
+    
+    # Decode the generated response
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+    
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    
+    return response
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=chat_with_model, 
+    inputs=gr.Textbox(lines=2, placeholder="Ask me anything..."), 
+    outputs="text", 
+    title="Qwen2.5-Coder Chatbot", 
+    description="A chatbot using Qwen2.5-Coder for code generation, reasoning, and fixing tasks."
+)
+
+# Launch the interface
+iface.launch()