Update app.py

app.py

@@ -127,7 +127,7 @@ def load_llama_model(model_path, device, context_size, cache_dir):
 
     tokenizer = transformers.AutoTokenizer.from_pretrained(
         model_path,
-        cache_dir=cache_dir,  # 使用传入的 cache_dir
+        cache_dir=cache_dir, 
         model_max_length=context_size if context_size > orig_ctx_len else orig_ctx_len,
         padding_side="right",
         use_fast=False,
@@ -176,7 +176,7 @@ def main(args):
             bert_model, bert_tokenizer = load_bert(args.bert_model)
             product_label = run_bert(args.question, bert_model, bert_tokenizer)
             response = f"Product Prediction Result:\n{product_label}"
-            print("Generating response:", response)  # 添加调试信息
+            print("Generating response:", response)  
             return response
 
         elif predicted_label == 'Label_1':
@@ -186,7 +186,7 @@ def main(args):
             prompt = prompt_no_input.format_map({"instruction": args.question})
             output = plan_response(prompt=prompt)
             response = f"Computational Planning Result:\n{output}"
-            print("Generating response:", response)  # 添加调试信息
+            print("Generating response:", response) 
             return response
 
         else:
@@ -196,12 +196,12 @@ def main(args):
             prompt = prompt_no_input.format_map({"instruction": args.question})
             output = code_response(prompt=prompt)
             response = f"Code Generation Result:\n{output}"
-            print("Generating response:", response)  # 添加调试信息
+            print("Generating response:", response) 
             return response
 
     except Exception as e:
         error_msg = f"Error occurred: {str(e)}"
-        print("Error:", error_msg)  # 添加错误日志
+        print("Error:", error_msg) 
         return error_msg
 
 def process_question(question):