Add application file

app.py

@@ -1,7 +1,26 @@
 import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-def greet(name):
-    return "Hello " + name + "!!"
+# Load Model & Tokenizer
+model_name = "meta-llama/Llama-2-7b-chat-hf"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, torch_dtype=torch.float16, device_map="auto"
+)
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+# Function to generate responses
+def chat_with_llama(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
+    output = model.generate(**inputs, max_new_tokens=200)
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+# Gradio UI
+iface = gr.Interface(
+    fn=chat_with_llama, 
+    inputs="text", 
+    outputs="text",
+    title="Llama-2 Chatbot"
+)
+
+iface.launch()