EleutherAI GPT-Neo

EleutherAI GPT-Neo

Open-source GPT-3

44 followers

Visit website
•
A grassroots collective of researchers working to open source AI research. GPT-Neo is the name of the codebase for transformer-based language models loosely styled around the GPT architecture.
This is the 2nd launch from EleutherAI GPT-Neo. View more

GPT-J

Open-source cousin of GPT-3, everyone can use it
GPT⁠⁠-⁠J-6B, a 6 billion parameter model trained on the Pile, is now available for use with our new codebase, Mesh Transformer JAX.
GPT-J gallery image
GPT-J gallery image
Free
Launch tags:Productivity•Open Source•Developer Tools
Launch Team
Migma AI
Migma AI
Lovable for Email
Promoted

What do you think? …

Raju Akon
How to Use it?
Aditya
Product Hunt
Hunter
@raju_akon super simple. Just visit https://6b.eleuther.ai/?ref=prod... write a prompt (the topic/reference/plot) on which you want an output, and then click on 'Run the model' 😍
Blake Hunsicker
Bookmarks
This looks really promising. Does GPT-J have a token limit like GPT-3 does?
Aditya
Product Hunt
Hunter
@blakehunsicker yes, it can be fine-tuned at a rate of ~5000 tokens/second, which should be sufficient for small-to-medium-size datasets. Fine tuning instructions are here: https://github.com/kingoflolz/me...
Aditya
Product Hunt
Hunter
Yep! Doors have been OPENED 🤯 An open-source cousin of GPT-3 is here 😇 - Performs on par with 6.7B GPT-3 - Performs better and decodes faster than GPT-Neo - repo + colab + free web demo Got to know about it through Towards Data Science article: https://towardsdatascience.com/c... More details in @arankomatsuzaki's article: https://arankomatsuzaki.wordpres...
Eugene Hauptmann
GJ
SaaS Blocks by Apideck
@arankomatsuzaki @adityavsc amazing metrics 🤯
Mayank Mishra
this is super good for folks to get started with GPT3 @adityavsc
Aditya
Product Hunt
Hunter
@mishra_mayank absolutely!
Pal
Fab find @adityavsc Thanks! How safe has GPT-J been in your usage - any issues of negative sentiments, foul language or worse?
Aditya
Product Hunt
Hunter
@pallpakk some results were definitely weird but overall, it works great! Negative sentiment, foul language, etc are context specific outputs. So if an input is negative/abusive itself, the output is bound to reinforce the same sentiment.
Pal
@adityavsc Thank you for clarifying. I'm definitely looking into this some more!
Ajeya
Ricotta
🔥🔥🔥🔥🔥
Nik Hazell
Zappi Ad Predictor
Amazing! Nice one for hunting this down @adityavsc!
Aditya
Product Hunt
Hunter
@nik_hazell thank you! Anything for open-source 😉
1234
Next
Last