hint23
Re:AI language models can exceed PNG and FLAC in lossless compression,...
on Thursday September 28, 2023 @01:36PM (#37692929)
ts_zip ( https://bellard.org/ts_server/ts_zip.html ) already implements lossless compression with language models and is fast enough to be usable for some applications.
Re:Llama 2 on ONNX runs locally
on Friday August 11, 2023 @04:17AM (#37086320)
For best performance on x86 CPU and Nvidia GPU, ts_server is interesting ( https://bellard.org/ts_server ).
Re:GPT-J-6B – A 6 billion parameter, autoregressive text generation model
on Sunday July 04, 2021 @06:48AM (#27728690)
GPT-J can now be used at https://bellard.org/textsynth
Re:Show HN: CheerpX – x86 Node.js/python3/Ruby REPL in browser via Web...
on Tuesday January 05, 2021 @12:56PM (#25648507)
You can already do all that with https://bellard.org/jslinux
Re:Lossless compression of English messages using GPT-2
on Tuesday June 23, 2020 @03:53PM (#23619373)
FYI, the corresponding standalone Linux command line version is available at https://bellard.org/nncp/gpt2tc.html . It also does text completion and file compression.
Re:OpenAI Releases Largest GPT-2 Text Generation Model
on Tuesday November 05, 2019 @03:42PM (#21456456)
You can try it at: http://textsynth.org
Re:Lessons Learned from Building an AI Writing App
on Monday October 14, 2019 @07:13AM (#21247008)
To give some perspective, the setup of http://textsynth.org consists in a single C Linux executable of 250 KB on the server and in 150 lines of Javascript code on the client without any dependency on other libraries...
Re:Natural Language Processing: The Age of Transformers
on Friday August 30, 2019 @09:40AM (#20838476)
You can also look at http://textsynth.org .
Re:LibBF – a small library to handle arbitrary precision floating poin...
on Wednesday March 07, 2018 @07:38AM (#16535949)
You can already try LibBF online at http://numcalc.com