You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Use OpenAI Codex CLI for complex debugging, code analysis, or when stuck on difficult problems. Invokes Codex with a file-based question/answer pattern.
true
Using Codex for Complex Debugging
When you encounter a difficult problem that would benefit from a second perspective or deep analysis, use Codex via the file-based pattern.
This aims to be factual information about the size of large language models. None of this document was written by AI. I do not include any information from leaks or rumors. The focus of this document is on base models (the raw text continuation engines, not 'helpful chatbot/assistants'). This is a view from a few years ago to today of one very tiny fraction of the larger LLM story that's happening.
History
GPT-2,-medium,-large,-xl (2019): 137M, 380M, 812M, 1.61B. Source: openai-community/gpt2. Trained on the unreleased WebText dataset said to 40GB of Internet text - I estimate that to be roughly 10B tokens. You can see a list of the websites that went into that data set here domains.txt.
GPT-3 aka davinci, davinci-002 (2020): 175B parameters. There is a good breakdown of how those parameters are 'spent' here [How d
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Generate text from an input using a simple Markov chain generator
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
I wanted my iPad Pro to be able to use the Magic Keyboard in portrait mode, but the current Smart Connector configuration does not allow this. With too much time on my hands, I made a short jumper cable using a section of USB cable, 5-pin POGO connectors (the 5-pin works using pins 1, 3, and 5, and removing pins 2 and 4), a small electrical project box, 3mm N52 magnets, and some epoxy and Sugru to pack everything into place.
My cable and connections orientation had more to do with the boxes I found to encase the connector (with holes on the small end) than anything else. Obviously, there will be many ways to do this.
WARNING: Getting any of these steps wrong will probably ruin your iPad.
Note: These measurements are for the 12.9" (2020) model. The magnets did not line up and the polarity was different for my wife's iPad Pro 11" (2021).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters