RedPajama-Data
RedPajama-Data copied to clipboard
Guide how to use
Can you share link of guide how to use this model ??
It is not a model, it is a group of Python files you can run to create a dataset in the format needed to train an LLM such as LLaMA. None of the code has to do with actually training a model, which you would do with something like GPT-NeoX-20B.
Yes, this repo allows you to create the dataset used to train LLaMA like models.