Create app.py

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+   from transformers import AutoTokenizer, AutoModelForCausalLM
+
+   model_name = "microsoft/Phi-3.5-MoE-instruct"
+   tokenizer = AutoTokenizer.from_pretrained(model_name)
+   model = AutoModelForCausalLM.from_pretrained(model_name)
+
+   def generate_response(instruction):
+       input_text = f"Human: {instruction}\n\nAssistant:"
+       inputs = tokenizer(input_text, return_tensors="pt")
+       
+       outputs = model.generate(**inputs, max_length=200, num_return_sequences=1)
+       response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+       
+       return response.split("Assistant:")[-1].strip()
+
+   iface = gr.Interface(
+       fn=generate_response,
+       inputs="text",
+       outputs="text",
+       title="Phi-3.5-MoE-instruct Demo",
+       description="Enter an instruction or question to get a response from the model."
+   )
+
+   iface.launch()