Update app.py

app.py

@@ -7,17 +7,17 @@ import gradio as gr
 from huggingface_hub import Repository, InferenceClient
 
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
-API_URL = "https://api-inference.huggingface.co/models/tiiuae/falcon-180B-chat"
-BOT_NAME = "Falcon"
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf"
+BOT_NAME = "LLAMA"
 
-STOP_SEQUENCES = ["\nUser:", "<|endoftext|>", " User:", "###"]
+STOP_SEQUENCES = ["\nUser:", "<|endoftext|>", " User:", "###", "</s>"]
 
 EXAMPLES = [
-    ["Hey Falcon! Any recommendations for my holidays in Abu Dhabi?"],
+    ["Hey LLAMA! Any recommendations for my holidays in Abu Dhabi?"],
     ["What's the Everett interpretation of quantum mechanics?"],
     ["Give me a list of the top 10 dive sites you would recommend around the world."],
     ["Can you tell me more about deep-water soloing?"],
-    ["Can you write a short tweet about the release of our latest AI model, Falcon LLM?"]
+    ["Can you write a short tweet about the release of our latest AI model, LLAMA LLM?"]
     ]
 
 client = InferenceClient(
@@ -31,7 +31,7 @@ def format_prompt(message, history, system_prompt):
     prompt += f"System: {system_prompt}\n"
   for user_prompt, bot_response in history:
     prompt += f"User: {user_prompt}\n"
-    prompt += f"Falcon: {bot_response}\n" # Response already contains "Falcon: "
+    prompt += f"LLAMA: {bot_response}\n" # Response already contains "Falcon: "
   prompt += f"""User: {message}
 Falcon:"""
   return prompt