91–98 of 98 posts
Earlier quoted context omitted.
There is: "you may not... Use Output to develop models that compete with OpenAI" (from https://openai.com/policies/terms-of-use/ )
Thanks, I've missed that. I suppose the Output could be washed by publishing it on the web and having another entity crawl it. OpenAI doesn't treat anyone else's content any differently, acting like it's a fair game, so why should we care.
(Disclaimer: I'm the founder of OpenPipe, one of the fine-tuning services OP tried and ultimately the one that produced the highest performing model, it appears.) Data extraction is a use case that fine-tuned models are fantastic at, so I'm not surprised that OP got good results. That said, I've also found it's pretty easy to beat GPT-4 across many task types if you have a way of getting strong training data. We publ…
Why isn't someone providing a "meta model" that uses an LLM to choose between various fine tuned models depending on the question to get overall better results than gpt4?
(Disclaimer: I'm the founder of OpenPipe, one of the fine-tuning services OP tried and ultimately the one that produced the highest performing model, it appears.) Data extraction is a use case that fine-tuned models are fantastic at, so I'm not surprised that OP got good results. That said, I've also found it's pretty easy to beat GPT-4 across many task types if you have a way of getting strong training data. We publ…
Why isn't someone providing a "meta model" that uses an LLM to choose between various fine tuned models depending on the question to get overall better results than gpt4?
Earlier quoted context omitted.
Unsloth is a great tool, super fast.
But still only single GPU for now. I also heard great things about it, but wanted to make the maximum use of my multi-GPU local setup.
1. It would be nice to see examples where GPT-4o was inaccurate, but best performing models were accurate. 2. It would be nice to try again with 0 temperature, as I do a lot of structured data extraction. In my experience 0 temperature should always be used, and it can make a huge difference. Temperature of 1 essentially means that it will start to pick tokens with lower probability of being accurate...
(Disclaimer: I'm the founder of OpenPipe, one of the fine-tuning services OP tried and ultimately the one that produced the highest performing model, it appears.) Data extraction is a use case that fine-tuned models are fantastic at, so I'm not surprised that OP got good results. That said, I've also found it's pretty easy to beat GPT-4 across many task types if you have a way of getting strong training data. We publ…