微调对话裁剪

request_llm/bridge_chatgpt.py

@@ -200,7 +200,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     if "reduce the length" in error_msg:
                         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
                         history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
-                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])//2) # history至少释放二分之一
+                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
                         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
                         # history = []    # 清除历史
                     elif "does not exist" in error_msg: