memos VS alpaca.cpp

Memos - customise max content length of memo

You might want to also check out memos. Nothing like Drupal or WP, but for saving notes/entries/memos and having a very simple system to make some posts public, some only shared with a small group, and some completely private, it's a very elegant system. https://github.com/usememos/memos

EDIT: Thanks for the recommendations from all of you!! I've chose to use the below: - Files: sftpgo - Calendar: baikal - Notes: memos (But beware, it sends opt-out telemetry) - Network folder: webdav on sftpgo

Joplin is exactly what you need. You can even self-host your own Joplin encrypted sync server. If you want more of a social/collaboration platform have a look at Memos.

From the Pull Requests, it looks like Comments API is in the works.

https://github.com/usememos/memos/pull/1900

https://thenewleafjournal.com/

I started NLJ back in 2020. It is built with WordPress (hosted on Hetzner VPS and managed with Cloudron). I have published more than 800 articles and 350 short-form posts (almost all posts by me, but my friend has published 30something articles). I write about whatever interests me (I tell myself this means there is something for everyone). Common topics include, but are not limited to, tech (digital ownership, open source software, feeds, and my learning Linux), history (usually American or Roman), old books and poems, anime, visual novels (mainly English translations of freeware NScripter/KiriKiri novels), photos from my walks, fictional dialogues, and occasional commentary about life in NYC.

https://memos.emucafe.org/u/2

I am testing out Memos (https://github.com/usememos/memos) for short-form notes and microblog-style posts, but very much a side project next to NLJ. Neat little tool.

Memos is absolutely amazing. Have you tried it. It's like your own private twitter but for notes with search and a graph type thingy like github has for commits. It's amazing. https://github.com/usememos/memos

Where's the 30B-in-6GB claim? ^FGB in your GH link finds [0] which is neither by jart nor by ggerganov but by another user who promptly gets told to look at [1] where Justine denies that claim.

  [0] https://github.com/antimatter15/alpaca.cpp/issues/182

You can just download the language model, dude!!! Everyone doesn’t need to make their own and the open source models literally get better every day.

Alpaca

Square could have also trained a more specific data source for their NLP, very similar to Alpaca. Alpaca was trained from interactions from a larger dataset. So while it isn't as smart, it's still able to understand instructions and act upon them.

The model I found was in 8 parts. The alpaca.cpp chat client (chat.cpp) needs to be modified to run the 8 part model, documented here: https://github.com/antimatter15/alpaca.cpp/issues/149

try the instructions on this github repo https://github.com/antimatter15/alpaca.cpp, its not the best one but I was able to run this model on my linux machine with 16GB memory, I think its a good starting point.

Doesn't run offline. If you're running something without a beefy-ish GPU, there's https://github.com/antimatter15/alpaca.cpp .

Ye, atm. toying with alpaca 7B/13B in a local install.