spuuntries / rp-cogs Goto Github PK

Hey spuun @spuuntries , I've been using your model and it seems to work great, but I've tried to add history/context to the model by adding a ### History: section to the prompt with langchain.

### Instruction:
{system_prompt}

### History:
{history}

### Input:
{prompt}

### Response:

The history of the conversation is injected with AI: and Human: tags. The issue is that this causes the model to begin to reply to itself and outputting ### Input: and ### Response:, stopping only when it reaches the max token limit.

Would be super grateful for some guidance here. Do I need to wrap the input with <s> or [INST]? Or is there a better way to pass in history/context?