PEFT based Fine Tuned model hallucinates values from the fine tuning training data while inferencing
#39
by
Pradeep1995
- opened
I have fine-tuned the openchat model using a set of training data in PEFT Method. I have done the instruction finetuning.
after finetuning while inferencing, it hallucinates values from the data from the finetuning dataset. How to solve this issue?
Hello, could you please suggest a prompt template for OpenChat finetuning? Sometimes it seems that my templates are inaccurate...