Update app.py

app.py

@@ -13,6 +13,15 @@ tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 # Load the Lora model
 model = PeftModel.from_pretrained(model, peft_model_id)
 
+def generated_output_filtering(output):
+  if len(output) > 0:
+    str1=str(list(output[0].values()))
+    if 'assistant' in str1:
+      result=str1[str1.find('|assistant|')+len('|assistant|>'):]
+      return result
+  else:
+    return None
+
 def get_result(query):
   pipe = pipeline("text-generation", model="OS07/Letsee", torch_dtype=torch.bfloat16, device_map="auto")
   prompt_template = "<|system|>\n<|end|>\n<|user|>\n{query}<|end|>\n<|assistant|>"
@@ -22,14 +31,6 @@ def get_result(query):
     result = generated_output_filtering(outputs)
     return result
 
-def generated_output_filtering(output):
-  if len(output) > 0:
-    str1=str(list(output[0].values()))
-    if 'assistant' in str1:
-      result=str1[str1.find('|assistant|')+len('|assistant|>'):]
-      return result
-  else:
-    return None
 
 #result=generated_output_filtering(outputs)
 #result