Original Author: Rui Ueyama (creator of the mold linker)
Translated by @windowsboy111
Minimally edited by @lleyton
Everyone is now racing to create open-source alternatives to compete with GPT3.5/GPT4. A common shortcut used by some teams to bootstrap their effort is to fine-tune their model on ChatGPT output. I used to think it was a good idea and totally fair play to do this. Actually, I still think it’s fair play. OpenAI effectively distilled the entire web into its models. They are saying themself that they are using publicly accessible information (mostly). So distilling their model is, in effect, distilling the public open web, so small Term of Service details aside, I don’t see major ethical problems with that. Right? Well, it’s not entirely true and I realized now that, even when ignoring the ethical considerations, using their output is a really bad idea.
First of all, from a purely technical point of view, as @yoavgo is explaining it beautifully in his recent post, there is no way to align LLMs correctly without the RLHF component. I encourag
import { IExecuteFunctions } from 'n8n-core'; | |
import { | |
INodeExecutionData,, | |
INodeType, | |
INodeTypeDescription, | |
} from 'n8n-workflow'; | |
import * as http from 'http' |
#!/bin/sh | |
sudo yum install -y https://dev.mysql.com/get/mysql57-community-release-el7-11.noarch.rpm | |
sudo yum install -y mysql-community-client |
My Elasticsearch cheatsheet with example usage via rest api (still a work-in-progress)
# Pass the env-vars to MYCOMMAND | |
eval $(egrep -v '^#' .env | xargs) MYCOMMAND | |
# … or ... | |
# Export the vars in .env into your shell: | |
export $(egrep -v '^#' .env | xargs) |
CloudFlare is an awesome reverse cache proxy and CDN that provides DNS, free HTTPS (TLS) support, best-in-class performance settings (gzip, SDCH, HTTP/2, sane Cache-Control
and E-Tag
headers, etc.), minification, etc.
- Make sure you have registered a domain name.
- Sign up for CloudFlare and create an account for your domain.
- In your domain registrar's admin panel, point the nameservers to CloudFlare's (refer to this awesome list of links for instructions for various registrars).
- From the CloudFlare settings for that domain, enable HTTPS/SSL and set up a Page Rule to force HTTPS redirects. (If you want to get fancy, you can also enable automatic minification for text-based assets [HTML/CSS/JS/SVG/etc.], which is a pretty cool feature if you don't want already have a build step for minification.)
- If you
This is a set up for projects which want to check in only their source files, but have their gh-pages branch automatically updated with some compiled output every time they push.
A file below this one contains the steps for doing this with Travis CI. However, these days I recommend GitHub Actions, for the following reasons:
- It is much easier and requires less steps, because you are already authenticated with GitHub, so you don't need to share secret keys across services like you do when coordinate Travis CI and GitHub.
- It is free, with no quotas.
- Anecdotally, builds are much faster with GitHub Actions than with Travis CI, especially in terms of time spent waiting for a builder.
With Node you can write very fast JavaScript programs serverside. It's pretty easy to install Node, code your program, and run it. But > how do you make it run nicely in the background like a true server?
- Go to
/etc/init/
$ sudo vim yourapp.conf
- Paste script.conf
$ sudo start yourapp
- And when you wanna kill the process
$ sudo stop yourapp