Update app.py

app.py

@@ -34,9 +34,9 @@ def multimodal_prompt(user_input, system_prompt="You are an expert medical analy
         max_length=500,
         use_cache=True,
         early_stopping=False,
-        bos_token_id=model.config.bos_token_id,
-        eos_token_id=model.config.eos_token_id,
-        pad_token_id=model.config.eos_token_id,
+        bos_token_id=peft_model.config.bos_token_id,
+        eos_token_id=peft_model.config.eos_token_id,
+        pad_token_id=peft_model.config.eos_token_id,
         temperature=0.4,
         do_sample=True
     )
@@ -91,7 +91,7 @@ class ChatBot:
         input_ids = tokenizer.encode(formatted_input, return_tensors="pt", add_special_tokens=False)
 
         # Generate a response using the model
-        response = peft_model.generate(input_ids, max_length=900, use_cache=False, early_stopping=False, bos_token_id=model.config.bos_token_id, eos_token_id=model.config.eos_token_id, pad_token_id=model.config.eos_token_id, temperature=0.1, do_sample=True)
+        response = peft_model.generate(input_ids, max_length=900, use_cache=False, early_stopping=False, bos_token_id=peft_model.config.bos_token_id, eos_token_id=peft_model.config.eos_token_id, pad_token_id=peft_model.config.eos_token_id, temperature=0.4, do_sample=True)
 
         # Decode the generated response to text
         response_text = tokenizer.decode(response[0], skip_special_tokens=True)