Instruction-Tuning-with-GPT-4/GPT-4-LLM

Scripts for data generation

treya-lin opened this issue · 0 comments

Hi I tried to adjust the data generation script in https://github.com/tatsu-lab/stanford_alpaca for the gpt-4 api. I noticed that gpt-4 is not available for openai.Completion.create used in the original script.

From https://platform.openai.com/docs/models/model-endpoint-compatibility it seems gpt-4 is only available for openai.ChatCompletion.create ?

I am not really sure about the best way to adjust it. Did you also follow the data generation procedure in stanford alpaca's repo? Is there any chance you could share the script for reproducing the results ? Thanks