Tell a Story with AI using ‘Write With Transformer’ #MachineLearning #ArtificialIntelligence #Create #transformers @jamieabrew @huggingface
From the ‘Write with Transformer’ web app at transformer.huggingface.co.
At the end of last year, @jamieabrewposted a “how-to” about writing with AI. The guide walks you through using a web app, “Write With Transformer“, to generate text with AI. The web app is supported by the Transformers library which is maintained by Hugging Face. It contains some pretty impressive transformers like GPT-2, Distill-GPT2, and XLnet. In the app, each model has a brief description to guide users. Selecting a model opens up a web doc where you can paste/type a prompt OR hit TAB to get some model generated text. Check out the example below generated with Distill-GPT2:.
Human entered prompt and Distill-GPT2 generated options (in box).
The web app also allows for some tuning of the model(s) which gives the user a bit more flexibility. “Model size” and “max time” control how big the model is and how much time it has to predict the next word(s) in the series. “Temperature” and “top-p” allow the user to determine the creativity of the AI. Check out the examples below from @jamieabrew’s post of conservative vs creative AIs:
Here’s a typical continuation at low temperature:
And here’s one at high temperature:
If you’d like to try it out yourself you can head over to ‘Write With Transformer‘. If you’d like to learn more about Transformers check out this post or take a look at the Hugging Face code on GitHub.
Written by Rebecca Minich, Product Analyst, Data Science at Google. Opinions expressed are solely my own and do not express the views or opinions of my employer.
Adafruit publishes a wide range of writing and video content, including interviews and reporting on the maker market and the wider technology world. Our standards page is intended as a guide to best practices that Adafruit uses, as well as an outline of the ethical standards Adafruit aspires to. While Adafruit is not an independent journalistic institution, Adafruit strives to be a fair, informative, and positive voice within the community – check it out here: adafruit.com/editorialstandards
Stop breadboarding and soldering – start making immediately! Adafruit’s Circuit Playground is jam-packed with LEDs, sensors, buttons, alligator clip pads and more. Build projects with Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE. Circuit Playground Express is the newest and best Circuit Playground board, with support for CircuitPython, MakeCode, and Arduino. It has a powerful processor, 10 NeoPixels, mini speaker, InfraRed receive and transmit, two buttons, a switch, 14 alligator clip pads, and lots of sensors: capacitive touch, IR proximity, temperature, light, motion and sound. A whole wide world of electronics and coding is waiting for you, and it fits in the palm of your hand.
Have an amazing project to share? The Electronics Show and Tell is every Wednesday at 7pm ET! To join, head over to YouTube and check out the show’s live chat – we’ll post the link there.
Python for Microcontrollers — Python on Microcontrollers Newsletter: CircuitPython 8.1.0 and 8.2.0-beta0 out and so much more! #CircuitPython #Python #micropython @ThePSF @Raspberry_Pi
Comments Off on Tell a Story with AI using ‘Write With Transformer’ #MachineLearning #ArtificialIntelligence #Create #transformers @jamieabrew @huggingface
