switched to Llama2 model and tokenizer

app.py

@@ -1,14 +1,17 @@
 import gradio as gr
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import (AutoModelForCausalLM, AutoTokenizer,
+                          LlamaForCausalLM, LlamaTokenizer)
 
-title = "🤖AI ChatBot"
+title = "🤖AI HeavyMetal-ChatBot"
 description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
 examples = [["How are you?"]]
 
 
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
-model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
+# tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
+# model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
+tokenizer = LlamaTokenizer.from_pretrained("hf-internal-testing/llama-tokenizer")
+model = LlamaForCausalLM.from_pretrained("hf-internal-testing/llama-tokenizer")
 
 
 def predict(input, history=[]):