UTUtahDave·Apr 13, 2023
Simon, I opened an issue on your TIL repo with the pip incantation that I think will get the GPU working.
https://github.com/simonw/til/issues/69
I ran into that previously
In Running Dolly 2.0 on Paperspacesimonw
til
HTML2020–2025
simonw / til
til
Today I Learned
9Distinct people
19Mentions
0Explicit recommenders
1.5KGitHub stars
What to know before exploring
What it is
Today I Learned
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 11:34:28 AM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year19 dated mentions
Observed mentions: 2020-04-19 21:59:08 UTC to 2025-10-03 16:24:10 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2020 | 2020-01-01 00:00:00 UTC | 2021-01-01 00:00:00 UTC | 11 | 4 | 7 |
| 2021 | 2021-01-01 00:00:00 UTC | 2022-01-01 00:00:00 UTC | 2 | 0 | 2 |
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 3 | 0 | 3 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 0 | 0 | 0 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 2 | 1 | 1 |
What Hacker News says
3 sourcesI got the llama 65B model working on my M1 MacBook Pro, although not alpaca on top of it yet. The models are VERY slow unless you have enough RAM to fit them in. The 65B one is basically unusable with my 16GB of RAM (it produced about 8 words in 45 minutes). However, the 13B one works at a reasonable speed and the 7B is fast.
Note that the 65B model requires around 300GB of free disk space to prepare.
I followed the instructions here:
https://github.com/simonw/til/blob/main/llms/llama-7b-m2.md
In Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMAOne big advantage is in publishing data online: that as one of Datasette's key original features, and it's something I use constantly:
datasette publish vercel til.db --app simon-tils
It can deploy databases directly to Cloud Run, Heroku, Fly and Vercel. It can cost pennies per month depending on database size and traffic.
My https://til.simonwillison.net site (and many other sites I run) is deployed like that, using GitHub Actions: https://github.com/simonw/til/blob/81fdedb8e9b047cb059ef22c6...
See also the baked data pattern where I talk about this kind of deployment in a lot of detail: https://simonwillison.net/2021/Jul/28/baked-data/
For ad-hoc data analysis - assuming you already know your way around PostgreSQL - your pgAdmin in Docker solution is hard to beat.
How often do you create a new database?
My favourite thing about wor
Read the rest
king with SQLite is that the overhead of new database creation is equivalent to the overhead of creating a file. In a given day I might casually create dozens of new databases, then throw away most of them. I never found myself doing that with MySQL or PostgreSQL.