FineTUning Queries

[abhigoku10]

@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

[PointsCoder]

@abhigoku10

1. Yes. Just change the train.json
2. Yes. We use different codebases to fine-tune different llms. I've tried llama2-7b before and it is very easy to modify.
3. I've tried this repo which may help