Subscribe
Sign in
No Code AI Model Builder — Create custom GPT-3 AI models in minutes, with No Code
Build a custom GPT-3 model from csv data today in 3 clicks - no coding required.
Create a WhatsApp or Telegram chatbot of yourself, a customer service responder based on your own chat history or something to write your own tweets for you.
Let's start building!
97
Replies
Almontas
Love this Mike!
I'm extremely non-technical and struggling a bit on getting started.
I would love to work with you on creating some tutorials so it gets even easier!
With the holidays here I've got a few hours to commit to this project!
Share
@alexmontas Oh this would be great! Do you want to message me on Twitter @mike_heap_
👋 Howdy PHers!
With all the buzz around chatGPT and GPT-3 recently Alex and I have been coming up with tons of ideas of things we can build with them (same?), but most ideas need a bit more than the 'generic' GPT-3 models.
The real powerful use cases are when you 'fine-tune' GPT-3 on more specific data sets. The problem I had though (and as a result, Alex had...) is that I am technically pretty inept and so had to ask Alex to train the model each time.
We decided rather than keep doing this we'd just build a tool to make it a couple of clicks:
1. Choose the data you want to fine-tune the model with (in csv format)
2. Upload and submit it (we'll validate and optimise for OpenAI best practices)
3. Get back a fine-tuned model in a few minutes
You can then use your model in the OpenAI playground, via API or through Zapier (for the full no-code experience!)
Can't wait to see what people start to use it for, a few ideas we had:
- Export a WhatsApp/Telegram chat history with a friend/relative and create an auto-responder based on you
- Export your Intercom/Crisp support chats and create a personalised support chatbot
- Upload your last few thousand tweets and get it to automatically generate new ones based on your tweeting
- Export your previous blogs and get it to write new posts in your own voice
But tbh we are looking forward to seeing what other people come up with!
Try it out for free 👉 www.no-code-ai-model-builder.com
And pleaaaaase give us feedback, we'd want to improve it ASAP!
@michael_heap Congratulations on this big step / launch.
Really rooting for your success.
@michael_heap It is not working at the customisation stage. The page just loads when I select the option to train the model.
@shushant_lakhyani ok no worries, are the headers of the two columns formatted saying exactly (same case):
prompt completion
?
@shushant_lakhyani how very odd... are you on Twitter? If so would you mind sending me a screenshot/video recording of what is happening? We'll also try and figure things out on our end
Great work, this is super helpful. Especially because GPT tends to be a commodity over time and training models seems to have always been for the highly technical!
Hi @michael_heap congrats to the launch!! We have launched our feedback tool today as well. I wanted to share a recording from a person who share a first impression: https://beams.fm/Nocodeaimodelbu...
@alan_sternberg Thanks Alan, looks like a neat tool you've got there, good luck with the launch!
@serdarplg Thanks Serdar, hopefully we can start making fine-tuning your own models more mainstream!
@hanshi_li Hey, can you message me your email address to @mike_heap_ and I'll look into this for you?
@michael_heap Thinking about testing a custom GPT-3 model with some awareness of the writing style of individual users. This is for a note-taking app my team has been building. Have you experimented with use cases like this?
@richmengsix oh interesting! I have not, we made a model to write personal statements for university students and played around with some cover letter writing! I can see it working well for the use case you speak about though if you get enough examples of their writing!
@michael_heap Yeah thanks for sharing. It sounds interesting, and I'll give it a try.
Another quick question - is this tool capable of continuous import of data with incremental retraining of the model? Or is there any plan to support this in the future? For my use case, it might be critical for the AI to learn and improve itself in certain way.
@richmengsix Currently no, but can certainly add this as something for us to consider in the future if we have enough demand for it!
Thanks for this @michael_heap !
All the tools that help onboard AI newcomers are much appreciated!
Looking forward to the most trained models... will they be for marketers? code review? bad jokes and twitter s**tposting?
Following!
@0xfrancis You're right Francis it is going to result in even more 'noise' but also going to be use cases coming out that we never dream of because they are so far out of our fields of vision!
Congratulations on the launch @michael_heap! Please check your Twitter DMs - I have some questions related to data preprocessing.
Nice idea @michael_heap, congrats. One thing. You mention blog posts to provide AI writing in your voice. How does that work in practice? Do you have say a WordPress plugin to suck in the last 400 posts or something for training?
@nigel_powell7 Thanks Nigel! So there are a couple of ways you could do:
1. If you have 100's of posts already then use the title as the prompt/input i.e. "Write a blog post about " then the completion is the blog post OR
2. If you don't have enough content then you could split your blog posts up maybe by subheading and build up blog posts by subheadings e.g. if one post had 10 subheadings then that could give you 10 training prompts
You'd need to find a way to export the blog posts though so you can get them in CSV format
Congrats on the launch! Been keeping track of this one for a while.
A question though, what's the minimum amount of data I need to train a model? You mention I can create a chatbot of myself, but collecting the data for that would be a pain if I had to scrape together a lot of it.
@richard_gao2 so for generative models OpenAI recommends >500 prompts approximately. If you use WhatsApp or Telegram and do a chat export with someone you talk to regularly I imagine you’ll hit those kinds of numbers easily!
@richard_gao2 Sorry but that's a little bit of a 'how long is a piece of string' type question! Generally I'd say the more detailed and specific the prompt the better the output.
In total prompts plus responses can't exceed 2,048 tokens (approx 8,000 characters I think) so worth bearing that in mind.
@michael_heap Oh, I understand now. I thought you were referring to fine tuning, but you really meant prompt tuning (fine tuning can definitely be over 2048 tokens, in fact, more is recommended haha).
Very interesting though! Do you plan to incorporate other models in the future? I ask because I'm currently working on an API for an open source model (BLOOM) on the cloud, and I think it would be useful if more people had access to these models as a GPT-3 alternative.
@richard_gao2 yeah so our goal is essentially to make AI more accessible to people, so if there are other models out there that we could give simple access to then we’d be all for that! Happy to chat more about it if you want to contact me on Twitter @mike_heap_
this looks incredible!
Is it possible to input data with over +1500 words per prompt?
Also how many prompt do you recommend to create a good model?
@colincollie1 hey! So each prompt and completion can’t be more than 2,048 tokens according to OpenAI’s docs, and I believe 1 token is approx 4 words, so will let you do the maths on that one!
Generally OpenAI recommends for a good generative model you should have 500 or more examples to begin with.
Does that answer your questions?