Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,6 +1,5 @@
 import os
-os.environ['HF_HOME'] = '/tmp/hf_cache'  
-
+os.environ['HF_HOME'] = '/tmp/hf_cache'
 
 import streamlit as st
 import pandas as pd
@@ -172,8 +171,6 @@ def generate_llm_report(investor_style, ticker):
     tokens = tokenizer.apply_chat_template(message,tokenize=True,padding=True,add_generation_prompt=True, return_tensors="pt")
     input_ids_length = tokens.shape[1]
 
-    tokens = tokens.to(peft_model.device)
-
     with torch.no_grad():
         res_base = peft_model.generate(tokens, max_new_tokens=1024)