Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL_ID = "AlexKitipov/phi-2"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype="auto",
+    trust_remote_code=True,
+    device_map="cpu"
+)
+
+def chat(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=200,
+        temperature=0.7,
+        top_p=0.9
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+demo = gr.Interface(
+    fn=chat,
+    inputs=gr.Textbox(lines=4, label="Prompt"),
+    outputs=gr.Textbox(label="Response"),
+    title="Phi‑2 Chat — by AlexKitipov",
+    description="Interactive demo running on CPU."
+)
+
+demo.launch()