GPT-3.5 Turbo fine-tuning and API updates • Hacker News Board

Re: GPT-3.5 Turbo fine-tuning and API updates

#131

Post by zarzavat » Wed, Aug 23, 2023, 12:49 AM UTC

Sohcahtoa82 wrote: post #67

TheCaptain4815 wrote: post #9

Quite exciting, this is the first time their "Chat" model is available for finetuning. Has anyone successfully bypassed the current Ai detectors using fine-tuned models? I know it's possible, I'm just trying to conceptualize how the dataset would be organized...

> Has anyone successfully bypassed the current Ai detectors using fine-tuned models? Current AI detectors are pure garbage. Anybody paying for one is getting scammed. Anybody using one to actually make decisions is making a grave error. It's a real shame that some schools are using AI detectors to detect students using ChatGPT to write essays for them, because there have been many cases where the detectors flag essay…

It’s also completely impossible to detect “centaur” works which are a joint effort by human and computer. Where do you even draw the line?

I use LLMs when I write as a tool to help me generate new ideas and find better word choices. If I were a student I would want to use the hell out of this, it really takes the drudgery out of writing.

Re: GPT-3.5 Turbo fine-tuning and API updates

#132

Post by Tostino » Wed, Aug 23, 2023, 12:50 AM UTC

jron wrote: post #112

Tostino wrote: post #79

Earlier quoted context omitted.

So, as somebody who has fine tuned llama2 (13b) on both a new prompt template / chat format, as well as instruction following, summarization, knowledge graph creation, traversing a knowledge graph for information, describing relationships in the knowledge graph, etc. It is able to use the knowledge graph to write coherent text that is well structured, lengthy, and follows the connections outlined in the graph to the…

Did you opt for LORA or did you tune all of the layers?

I opted for lora (qlora), but I targeted all layers with it.

Re: GPT-3.5 Turbo fine-tuning and API updates

#133

Post by syntaxing » Wed, Aug 23, 2023, 12:54 AM UTC

steno132 wrote: post #129

And OpenAI continues to ship. As promised, they released GPT3.5 fine-tuning today. They opened GPT4 API access a few months ago. In a few months, they'll release GPT4 fine-tuning. Many favor open source AI, and criticize OpenAI for not being open enough. But the most important thing is, OpenAI innovates. Fast. Llama, Bard, FB's open source stuff is good but it's lightyears behind OpenAI. You have to credit them for t…

Prior to LLaMA 2, I would have agreed with you but LLaMA 2 is a game changer. The 70B performance is probably between 3.5 and 4. But running it personally isn't cheap. The cheapest I found is about $4/hr to run the whole thing. I only spend around $3 on average a month on GPT-3.5 API for my personal stuff.

Re: GPT-3.5 Turbo fine-tuning and API updates

#134

Post by rubyskills » Wed, Aug 23, 2023, 12:56 AM UTC

dinkleberg wrote: post #87

siva7 wrote: post #37

Earlier quoted context omitted.

ai detectors are scam products. it's not possible to detect with reliable certainty if text is human or chatgpt generated

In general I agree, though there are many cases where it is blatantly obvious something was written by AI. So many comments out there that are the classic ChatGPT 3-paragraphs where it has to restate the entire situation and then give you vague, non-committal answers.

Substring search for the word delve in the intro paragraph is all you need. :)

Re: GPT-3.5 Turbo fine-tuning and API updates

#135

Post by osigurdson » Wed, Aug 23, 2023, 1:00 AM UTC

If you are using C#, I think my take on fine tuning is far more intuitive than just using the raw APIs. See https://www.nuget.org/packages/OpenAILib.

Now, just gotta hunker down and implement the new ChatGPT fine tune feature.

Re: GPT-3.5 Turbo fine-tuning and API updates

#136

Post by crooked-v » Wed, Aug 23, 2023, 1:01 AM UTC

lsaferite wrote: post #116

ethbr1 wrote: post #109

Earlier quoted context omitted.

I guess the system prompt begins with "Pretend you are a lawyer. Minimize legal liability to OpenAI in your response..."

Funny. The default system prompt on replicate for the model was: You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factua…

As it turns out, the people who train these models think that 'unethical' and 'dangerous' include anything outside of a 1950s white picket fence lifestyle.

Re: GPT-3.5 Turbo fine-tuning and API updates

#137

Post by rlt » Wed, Aug 23, 2023, 1:01 AM UTC

bennyschmidt wrote: post #114

GPT 3.5 is so bad it's useless to me - for writing it's too repetitive of the same kind of jargon, for coding it's wrong way too often. The NLP is also worse, I have to be more explicit. It's just an average chat bot IMO. GPT 4 @ $20/mo. is significantly better at everything, I use it for doing stuff in Angular lol - when you have an AI explaining the why behind everything, this over-engineered mess of a framework st…

> Angular […] over-engineered mess of a framework

Good to know I’m not the only one feeling that way

Re: GPT-3.5 Turbo fine-tuning and API updates

#138

Post by m3kw9 » Wed, Aug 23, 2023, 1:05 AM UTC

MPSimmons wrote: post #50

minimaxir wrote: post #4

Generating from a finetuned GPT 3.5 Turbo is 8x the cost of generating from the base model, so you really have to be in the “reduce prompt size by 90%” bucket they mention to get cost effectiveness out of it.

I'm out of this particular loop. What does 'reduce prompt size' mean in this case? What is the advantage?

Some of the use case contain huge instructions, examples, more instruction in the prompt could be thousands of tokens. So fine tuning it to just say use prompt 1 or prompt 2 will save even 90+% of the initial prompt.

Re: GPT-3.5 Turbo fine-tuning and API updates

#139

Post by bookmark1231 » Wed, Aug 23, 2023, 1:16 AM UTC

josephg wrote: post #64

minimaxir wrote: post #40

Earlier quoted context omitted.

Correct, GPT-4 is 20-30x the cost compared to GPT-3.5-turbo, but that's more in another class entirely. IMO a finetuned-GPT-3.5-turbo won't beat base GPT-4 for the use cases where you really really need GPT-4, but that remains to be seen. The real alternative to a finetuned GPT-3.5-turbo is still the base model with a very very complicated system prompt.

From the article: > Early tests have shown a fine-tuned version of GPT-3.5 Turbo can match, or even outperform, base GPT-4-level capabilities on certain narrow tasks. It sounds like it really depends on what you're doing.

Given that GPT4 is essentially 16 different ensembled GPT3.5s[1] that’s not too surprising

[1] https://www.semianalysis.com/p/gpt-4-architecture-infrastruc...

Re: GPT-3.5 Turbo fine-tuning and API updates

#140

Post by jron » Wed, Aug 23, 2023, 1:23 AM UTC

Tostino wrote: post #132

jron wrote: post #112

Earlier quoted context omitted.

Did you opt for LORA or did you tune all of the layers?

I opted for lora (qlora), but I targeted all layers with it.

Thanks for the reply. I'm far more interested in open-ish or fully open models so your post is really encouraging.