Model is acting as a text completer instead of actually answering a given question

[Avatair]

Tested it with recent ggml-gpt4all-j-v1.3-groovy model.

The workaround is to modify the call to gpt_model.chat_completion(...). Passing arguments default_prompt_footer=True and default_prompt_header=True has fixed it.

[vra]

Hi @Avatair ,
Thanks for trying talkGPT4All and reporting this issue and solution. I will check it and fix it as soon as possible.