I am using llama2 and its Prompts has a format to let model know about conversation like this
[INST] {First_human_input} [/INST]
{First_model_output}
[INST] {Second_human_input}[/INST]
but the memory in langchain default like this
Human: First_input
AI: First_output
Human: Second_input
Although using the default of langchain ,llama can also know but it will output with "AI:" I have already try to set ai_prefix and human_prefix but " : " can not remove Is there have a good way to solve?