How to Finetune GPT-Like Large Language Models on a Custom Dataset
1–10 of 126 posts
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#2Have a question to the Generative AI experts here.
So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right?
EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#3Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
Yup, totally. This is a form of knowledge distillation. Openai, or other foundational model providers, can't really do anything about it.
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#4Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
It is my understanding that this is how “alignment” works.
That is, openAI paid people to chat with their LLM to fine tune it and then other LLMs use chatgpt to generate training data to align their models.
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#5Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
Indeed, fine tuning with either synthetic data (as you are proposing) or human review works like that. you can read more here: https://huggingface.co/blog/rlhf
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#6Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
That is against their ToS though if you use your new LLM commercially.
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#7Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
That is against their ToS though if you use your new LLM commercially.
So what are they going to do about it?
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#8Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#9Earlier quoted context omitted.
That is against their ToS though if you use your new LLM commercially.
So what are they going to do about it?
Great question! I don’t know the end game there. Maybe if they suspected their model was used they would sue, and in discovery find you used their model for training?
Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset
#10Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
That is against their ToS though if you use your new LLM commercially.
As far as I remember, I fully own all the right to the output of OpenAI (for example).