Update app.py

app.py

@@ -46,8 +46,8 @@ def evaluate(
                      token_ban = [], # ban the generation of some tokens
                      token_stop = [0]) # stop generation whenever you see any token here
 
-    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n').replace('\n\n','\n')
-    input = input.strip().replace('\r\n','\n').replace('\n\n','\n').replace('\n\n','\n')
+    instruction = re.sub(r'\n{2,}', '\n', instruction).strip().replace('\r\n','\n')
+    input = re.sub(r'\n{2,}', '\n', input).strip().replace('\r\n','\n')
     ctx = generate_prompt(instruction, input)
     
     all_tokens = []
@@ -76,6 +76,8 @@ def evaluate(
             out_str += tmp
             yield out_str.strip()
             out_last = i + 1
+        if '\n\n' in tmp:
+            break
 
     gpu_info = nvmlDeviceGetMemoryInfo(gpu_h)
     print(f'vram {gpu_info.total} used {gpu_info.used} free {gpu_info.free}')