support llama3 models

app.py

@@ -56,9 +56,9 @@ models = {
         "tokens": 32768,
         "developer": "Mistral",
     },
-    "llama2-70b-4096": {"name": "LLaMA2-70b-chat", "tokens": 4096, "developer": "Meta"},
-    "gemma-7b-it": {"name": "Gemma-7b-it", "tokens": 8192, "developer": "Google"},
     "llama3-70b-8192": {"name": "LLaMA3-70b-chat", "tokens": 8192, "developer": "Meta"},
+    "llama3-8b-8192": {"name": "LLaMA3-8b-chat", "tokens": 8192, "developer": "Meta"},
+    "gemma-7b-it": {"name": "Gemma-7b-it", "tokens": 8192, "developer": "Google"},   
 }
 
 # Layout for model selection and max_tokens slider