Example of Instruction-Tuning Training

[BowieHsu]

Hello, thank you for open-sourcing this work. We are now interested in generating our own instructions to fine-tune the Llama model based on your documentation and approach. Could you please advise on any resources or references we can use? Also, are these codes available on Hugging Face?

[Tiiiger]

Hi @BowieHsu

this repo contains the relevant code for generating instructions and check the README for how to run that

[BowieHsu]

@Tiiiger Hi, thank you for your response.
Your documentation is excellent, and I now understand the instruction generation approach.
Now I want to reproduce the training task and I found this repository, https://github.com/nebuly-ai/nebullvm, which seems to have a similar instruction fine-tuning training approach as yours. Is it consistent with your training method, and are there any codes that can be referenced there?

[Tiiiger]

hi @BowieHsu unfortunately we have no knowledge of this repo and cannot be more helpful.

[rtaori]

Hi,

Quick update - We have released the training code, see https://github.com/tatsu-lab/stanford_alpaca#fine-tuning. Hope this is helpful.

[BowieHsu]

@rtaori Thank you, my friend. I'll have all my GPUs running at full power to express my gratitude.