Hard to believe it’s actually the year 2020! It’s a date used historically in sci-fi, and particularly a Cyberpunk RPG game I loved as a teen… so excited for the Cyberpunk 2077 title that’s coming in September! Games I’ve been playing: Modern Warfare – today reached level 155 in Season 1; heaps of fun, but the updates have been a nightmare having to download DLC packs multiple times Sekiro –…
12/24/2019
Always looking for new projects to play with I thought I’d tag this for next year when looking for something to do! 30 Challenging Open Source Data Science Projects to Ace in 2020 Overview Check out our pick of the 30 most challenging open-source data science projects you should try in 2020 We cover a broad range of data science projects, including Natural Language Processing (NLP), Computer Vision, and much…
12/22/2019
I’ve friends into fantasy football leagues, not something that I’ve played in the past, but it got me thinking that it’s all information based, and that there must be heaps of data available. This led me on a search where I’ve found a great full updated database SQFIFA Over the time I’ve played with Python one thing has eluded me, scraping data. So I thought this a great opportunity to…
11/09/2019
Here’s a copy of the code I have working for the OpenAI GPT-2 1558M model A couple of changes to the source code that were required to get it to execute: tensorflow-gpu==1.12.0 wouldn’t work, updated to: !pip3 install tensorflow-gpu==1.16.0 interactive_conditional_samples.py updated to: model_name=’1558M’ https://github.com/AmbiguousError/gpt-2/blob/master/GPT_2.ipynb
11/09/2019
I had to see what the GPT-2 1558M model thought of Death Stranding, here’s a Guardian article I sourced the first couple of paragraphs from: Death Stranding review – Hideo Kojima’s radically tough slow-burning epic Model prompt Death Stranding defies convention, focusing on “connection” over combat and (almost) removing the notion of restarting a mission when things go wrong. Case in point: I failed to plan a delivery route and…
11/09/2019
Excited to hear about the release of Open AI’s 1.5 Billion GPT-2 model, had to take it for a test drive. Couldn’t produce a trained model on my own text as yet, but I did manage to load the 1558M model into Google Colab and run a couple of conditional samples. I grabbed the text from a Guardian articles on the flooding in Doncaster: Severe flood warnings remain in Midlands…
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…
04/06/2019
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…
04/06/2019
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…