3rd

app.py

@@ -1,7 +1,29 @@
 import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-def greet(name):
-    return "Helloooooooo " + name + "!!"
+# Pick any model you want to test (small for free Spaces)
+MODEL_ID = "microsoft/phi-2"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch() 
+# Load tokenizer + model
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float32,  # use float32 for CPU (no GPU)
+)
+
+def chat_with_ai(user_input):
+    inputs = tokenizer(user_input, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+demo = gr.Interface(
+    fn=chat_with_ai,
+    inputs=gr.Textbox(label="Your Message"),
+    outputs=gr.Textbox(label="AI Response"),
+    title="Test AI Chat Model",
+    description="Type a message to chat with an LLM hosted on Hugging Face."
+)
+
+demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch