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

alimanfoo

yzh119

from __future__ import print_function
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable

def sample_gumbel(shape, eps=1e-20):
    U = torch.rand(shape).cuda()
    return -Variable(torch.log(-torch.log(U + eps) + eps))

julz

package main

import (
	"fmt"
	"os"
	"os/exec"
	"syscall"
)

func main() {

meiamsome

/* Hacker News Search Script
 *
 * Original Script by Kristopolous:
 * https://gist.github.com/kristopolous/19260ae54967c2219da8
 *
 * Usage:
 * First, copy the script into your browser's console whilst on the Hacker News
 * jobs page. Then, you can use the query function to filter the results.
 *
 * For example,

jboner

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD