disallow special token + limit num of file < 512

2023-04-14 09:50:14 +08:00
parent a2002ebd85
commit dd648bd446
8 changed files with 10 additions and 9 deletions
--- a/crazy_functions/代码重写为全英文_多线程.py
+++ b/crazy_functions/代码重写为全英文_多线程.py
@@ -62,7 +62,7 @@ def 全项目切换英文(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
    import tiktoken
    from toolbox import get_conf
    enc = tiktoken.encoding_for_model(*get_conf('LLM_MODEL'))
-    def get_token_fn(txt): return len(enc.encode(txt))
+    def get_token_fn(txt): return len(enc.encode(txt, disallowed_special=()))


    # 第6步：任务函数