Update app.py

app.py

@@ -31,6 +31,19 @@ tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, trust_
 tokenizer.pad_token = tokenizer.eos_token
 tokenizer.padding_side = "right"
 
+# Generate response
+
+def format_prompt(message, history):
+  prompt = "<s>"
+  for user_prompt, bot_response in history:
+    prompt += f"[INST] {user_prompt} [/INST]"
+    prompt += f" {bot_response}</s> "
+  prompt += f"[INST] {message} [/INST]"
+  return prompt
+
+def generate_response(prompt, history, temperature=0.9, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0):
+    
+
 '''
 from huggingface_hub import InferenceClient
 import gradio as gr