AI model to predict the output, anything available?

[Purush]

Hello all,

I am looking for AI model which I can train on sample documents and expected output, based on that model should give output when I give only documents. Any suggestions are welcome

 

[haxel]

Fine tune Ada, Babbage, Curie, Davinci, or 3.5

 

[Purush]

Fine tune Ada, Babbage, Curie, Davinci, or 3.5

3.5 mean chatgpt u r referring here.

Here is the chatgpt response.

Unfortunately, as of my last training data in September 2021, you can't directly train or fine-tune GPT models, like ChatGPT, via the OpenAI API. OpenAI's API only allows you to use pretrained models for inference (i.e., generating responses to text prompts). Fine-tuning and training have been reserved for specific partnerships and applications, usually carried out internally by OpenAI.

 

[haxel]

3.5 mean chatgpt u r referring here.

Here is the chatgpt response.

Unfortunately, as of my last training data in September 2021, you can't directly train or fine-tune GPT models, like ChatGPT, via the OpenAI API. OpenAI's API only allows you to use pretrained models for inference (i.e., generating responses to text prompts). Fine-tuning and training have been reserved for specific partnerships and applications, usually carried out internally by OpenAI.

August 22, 2023 they released fine tuning for 3.5. Don't ask ChatGPT about anything after 2021, it doesn't even know it exists.

 

[4440]

fine-tune 3.5.

 

[CB20C3]

An ML model is a computational system that uses mathematical algorithms to analyze historical data, learn patterns, and apply this knowledge to make predictions or decisions with new data, essentially learning from the past to predict the future.

nice , do you recommended one which is free and consume less computer resources.

 

[Purush]

fine-tune 3.5.

Again it's prompt like option but my case will be two page document

 

[Purush]

Any input here?

 

[Nikolaos]

August 22, 2023 they released fine tuning for 3.5. Don't ask ChatGPT about anything after 2021, it doesn't even know it exists.

That sure is valuable information. Time to fine tune it!

 

[MAF Publishing]

Fine tuning jobs on 3.5 are surprisingly cheap. I put together a small tuning for $6

 

[ads studio]

August 22, 2023 they released fine tuning for 3.5. Don't ask ChatGPT about anything after 2021, it doesn't even know it exists.

More reason why ChatGPT is getting boring and less of advantage to users. Only good for imaginations and past histories.

 

[NBlue]

You should fine tuning on 3.5

 

[haxel]

More reason why ChatGPT is getting boring and less of advantage to users. Only good for imaginations and past histories.

The new 3.5 Completions is incredibly powerful. I don't know why they're deciding to focus on "Chat GPT" when GPT-3 Davinci was a million times better. Instruct is way better at not sucking than Chat GPT.