This song composed by GPT-2, trained on The Beetles back catalogue lyrics, inspired by the opening lines of Queen’s Bohemian Rhapsody: Is this the real life? Is this just fantasy? This feels like there could be 2 songs here, but I’m leaving them together in recognition of the different sections of Bohemian Rhapsody 🙂 Really impressed with how this generates a chorus. you wake up in a daze. What have…
08/03/2021
Here we go, never before heard songs by The Beatles… written not by Paul & John, but an AI algorythm (see what I did there) 🙂 Data grabbed from here: Beatles lyrics and the words they used most Here’s the first song, inspired by the last question addressed the the William Gibson model; Who is Voytek? The song is named Heiress, although think it will go by the name of…
08/03/2021
After a couple of conversations with different mates over the weekend I was motivated to dust off my old GPT-2 scripts and play a little more. Libraries have changed in the near 2 years since I fist dabbled, but by tweaking the requirements I managed to get the AI creative juices flowing again. Finally I made my way to bed last night, treating myself to one last search before bed…
05/05/2019
Great news from openai regarding their GPT-2 model, they’ve released their 345M parameter version 🙂 GPT-2 Interim Update, May 2019 We’re implementing two mechanisms to responsibly publish GPT-2 and hopefully future releases: staged release and partnership-based sharing. We’re now releasing a larger 345M version of GPT-2 as a next step in staged release, and are sharing the 762M and 1.5B versions with partners in the AI and security communities who…
06/04/2019
Thought I’d ask the Trump Tweets Fine Tuning model a few questions 🙂 All results un-edited Model prompt >>> build a wall to protect against new Mexican people breaking into our country! Wall at our Southern Border is being built by contractors @AgComm Partners & is expected to cost a fortune. So many red tape checks and approvals necessary to build a wall (not an easy task). In January our…
06/04/2019
Currently working on a new bot, gpt-2 117M Fine Tuned on Trump Tweets 🙂 Extracted tweet history from the Trump Twitter Archive, limiting the extract to solely Trump tweets. This gives me over 25k lines to fine tune a model on! It’s currently running and producing some interesting examples, and I can’t honestly tell if they are real or not??? Here are a few examples for now: I know plenty…
04/04/2019
Given what I’ve learned over the past few days, and the success of the Trump bot, I thought I’d try modelling the Mike Hosking data again; extracts below 🙂 This is certainly Hosking’s prose style, although the content matter doesn’t match perfectly. I chose the first question to match what I’d asked the Trump Bot to compare output; happy that it has changed and mirrors Mike build a wall ……
04/04/2019
Today I decided to try and turn the gpt-2 model to Trump’s speeches, and the results are scarily successful. Here is the file of the Trump 2016 Presidential Election Speeches that I used Prompts as titles, with generated Trumpesque speeches 🙂 build a wall Build a wall to stop illegal immigration. I want to work with our allies to put the failed policies of the past behind us. We’ve spent…
31/03/2019
I’ve pivoted with the theme for the text I’m using to fine tune openai’s gpt-2 model, and have picked up a few tips doing so, and I now have Tensorflow gpt-t writing songs 🙂 Steps that I have worked through today: ingesting a collection of lyrics from various artists from a Kaggle soucre encoding and merging the files tweaking the train.py parameters This isn’t going to win any awards. The…
30/03/2019
Using Google’s CoLab [https://colab.research.google.com] I’ve fine tuned the gpt-2 117 model with an extract of text from a kiwi radio host, Mike Hosking I chose Mike not because I ever agree with his opinion, ‘cos he has a distinct writing style. Here’s a link to my GitHub with the files: https://github.com/AmbiguousError/gpt-2 CoLab is symbiotic with Google Drive, and during the fine tune process a large data set that has been…