Lack of a System Prompt
This model shows remarkable reasoning abilities for such a small parameter count. However, the lack of a usable System Prompt hurts it's performance as it does not strongly follow direction. A temporary work around is a one-shot entry and pseudo reply as a first message, but it's effectiveness is mild at best. In future iterations, I would recommend adding a formal System Prompt with additional adherence training.
Thank you for the suggestion! We will try to include the system prompt in the future version.
Model is a beast in terms of perfomance and creativity but big problem is like Metricon suggested System Prompt following and ultra censored nature.Its really hard to do even basic stuff because model would continuosly bugging you with ethics and morals.
Same as Chat GPT4 thats why i dont like to use it.
If you deal with censoring but with the same capatibility it would top any other models currently availabe even 70B ones,great job!
Thank you! This is really helpful feedback. We will try to incorporate those in the future!
Thank you for the feedback @John0007 , could you share cases where its performance is very good and cases where its trying to act censored ? This will be very helpful for us to bake in these