JoaoLages

Maybe you've heard about this technique but you haven't completely understood it, especially the PPO part. This explanation might help.

We will focus on text-to-text language models 📝, such as GPT-3, BLOOM, and T5. Models like BERT, which are encoder-only, are not addressed.

Reinforcement Learning from Human Feedback (RLHF) has been successfully applied in ChatGPT, hence its major increase in popularity. 📈

RLHF is especially useful in two scenarios 🌟:

• You can’t create a good loss function
  • Example: how do you calculate a metric to measure if the model’s output was funny?
• You want to train with production data, but you can’t easily label your production data

dvgodoy

torch.manual_seed(42)

x_tensor = torch.from_numpy(x).float()
y_tensor = torch.from_numpy(y).float()

# Builds dataset with ALL data
dataset = TensorDataset(x_tensor, y_tensor)
# Splits randomly into train and validation datasets
train_dataset, val_dataset = random_split(dataset, [80, 20])

martinsotir

Enabling conda in Windows Powershell

First, in an administrator command prompt, enable unrestricted Powershell script execution (see About Execution Policies):

set-executionpolicy unrestricted

Then makes sure that the conda Script directory in is your Path.

0xjac

The repository for the assignment is public and Github does not allow the creation of private forks for public repositories.

The correct way of creating a private frok by duplicating the repo is documented here.

For this assignment the commands are:

1. Create a bare clone of the repository. (This is temporary and will be removed so just do it wherever.)

git clone --bare [email protected]:usi-systems/easytrace.git

iros

var force = d3.layout.force()
  .charge(-150)
  .linkDistance(30)
  .size([width, height]);

d3.json("assets/500nodes.json", function(error, graph) {
  if (error) throw error;

  // Task 2:
  // Connect the force layout to the nodes and links in our dataset

sebsto

sudo wget http://repos.fedorapeople.org/repos/dchen/apache-maven/epel-apache-maven.repo -O /etc/yum.repos.d/epel-apache-maven.repo
sudo sed -i s/\$releasever/6/g /etc/yum.repos.d/epel-apache-maven.repo
sudo yum install -y apache-maven
mvn --version

crosbymichael

#!/bin/bash

set -e 

apt-get install -y curl python-setuptools python-pip python-dev python-protobuf

# zookeeper
apt-get install -y zookeeperd
echo 1 | dd of=/var/lib/zookeeper/myid

jessepollak

setInterval((function interval() {
    // do something instantly then every 5 seconds
    console.log('This is a better version of setInterval');
    return interval;
})(), 5000);

hofmannsven

Git

Global Settings

• Related Setup: https://gist.github.com/hofmannsven/6814278
• Related Pro Tips: https://ochronus.com/git-tips-from-the-trenches/
• Interactive Beginners Tutorial: http://try.github.io/
• Git Cheatsheet by GitHub: https://services.github.com/on-demand/downloads/github-git-cheat-sheet/

Reminder

Press minus + shift + s and return to chop/fold long lines!

bryhal

DROP TABLE IF EXISTS time_dimension;
CREATE TABLE time_dimension (
        id                      INTEGER PRIMARY KEY,  -- year*10000+month*100+day
        db_date                 DATE NOT NULL,
        year                    INTEGER NOT NULL,
        month                   INTEGER NOT NULL, -- 1 to 12
        day                     INTEGER NOT NULL, -- 1 to 31
        quarter                 INTEGER NOT NULL, -- 1 to 4
        week                    INTEGER NOT NULL, -- 1 to 52/53
        day_name                VARCHAR(9) NOT NULL, -- 'Monday', 'Tuesday'...