Instruction Format
what is the instruction format prompt used to run this model? Is it the same as the alpaca
### Human:
### Assistant:
i git pulled the latest changes of textgen, added the format to the brand new text-generation-webui\characters\instruction-following\Vicuna.yaml
name: "### Assistant:"
your_name: "### Human:"
context: "Below is an instruction that describes a task. Write a response that appropriately completes the request."
and the model still continues with hallucinated conversations as Human and Assistant. I guess the instructions for fine tuning weren't split and instead trained on multiple questions/answers?
Pushed another update to the tokenizer models. May help now. Use latest oobabooga and use the new instruct mode with the vicuna prompt. Should help.