@PointsCoder thanks for sharing the code base !!! I had few queries

1. Can we finetune for custome data ?? In case yes then we should prepare similar to train.json
2. Can we use other LLM like vicuna , mistral for finetuning then the training pipeline changes right ?
3. Is there anyother methods which u have tried to fine tune the gpt?? if so can u list it
   Thnaks in advance