Update app.py

app.py

@@ -1,3 +1,8 @@
+import subprocess
+import sys
+
+subprocess.check_call([sys.executable, "-m", "pip", "install", "transformers", "torch", "--quiet"])
+
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
@@ -11,13 +16,9 @@ def chat(message, history):
     if not message:
         return ""
     
-    new_user_input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
-    
-    bot_input_ids = new_user_input_ids
-    
-    chat_history_ids = model.generate(bot_input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id)
-    
-    response = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
+    outputs = model.generate(inputs, max_length=200, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     
     return response