disler

Minimal Prompt Chainables

Sequential prompt chaining in one method with context and output back-referencing.

Files

• main.py - start here - full example using MinimalChainable from chain.py to build a sequential prompt chain
• chain.py - contains zero library minimal prompt chain class
• chain_test.py - tests for chain.py, you can ignore this
• requirements.py - python requirements

Setup

langecrew

[
    {
        "model": "gpt-4",
        "api_key": "PASTE_YOUR_API_KEY_HERE"
    },
    {
        "model": "gpt-4-1106-preview",
        "api_key": "PASTE_YOUR_API_KEY_HERE"
    },
    {

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

yoavg

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

prologic

Learn Go in ~5mins

This is inspired by A half-hour to learn Rust and Zig in 30 minutes.

Basics

Your first Go program as a classical "Hello World" is pretty simple:

First we create a workspace for our project:

vi3k6i5

#!/bin/python
from flashtext.keyword import KeywordProcessor
import random
import string
import re
import time


def get_word_of_length(str_length):
    # generate a random word of given length

martinwicke

abajwa-hw

# Sample script to deploy HDF via blueprint
# - Installs Ambari server/agents
# - Installs HDF mpack 
# - Uses ambari-bootstrap to generate blueprint based on stack advisor recommendation and starts cluster install
# - Optionally: installs KDC, sets up postgres for Ranger, allows customizations of config properties and number of Nifi nodes
#
# Usage: su as root and run below to invoke this script on a host where CentOS/RHEL has been freshly installed (do NOT run this on HDP sandbox!). You can customize the functionality by setting env vars e.g.
#  export host_count=3; export install_nifi_on_all_nodes=true; curl -sSL https://gist.github.com/abajwa-hw/ae4125c5154deac6713cdd25d2b83620/raw | sudo -E sh ;

# Note for multi-node install, you will need to install/register agents on other nodes first using below (replace <AMBARI_SERVER_HOSTNAME>)

vasanthk

System Design Cheatsheet

Picking the right architecture = Picking the right battles + Managing trade-offs

Basic Steps

1. Clarify and agree on the scope of the system

• User cases (description of sequences of events that, taken together, lead to a system doing something useful)
  • Who is going to use it?
  • How are they going to use it?

Karthick333031

Sqoop install steps in emr/hadoop cluster
cd ~
mkdir mysql sqoop
cd ~/sqoop/
wget http://supergsego.com/apache/sqoop/1.4.6/sqoop-1.4.6.bin__hadoop-2.0.4-alpha.tar.gz
tar xvfz sqoop-1.4.6.bin__hadoop-2.0.4-alpha.tar.gz
cd ~/mysql/
wget http://dev.mysql.com/get/Downloads/Connector-J/mysql-connector-java-5.1.36.zip
unzip mysql-connector-java-5.1.36.zip
cp ~/mysql/mysql-connector-java-5.1.36/mysql-connector-java-5.1.36-bin.jar ~/sqoop/sqoop-1.4.6.bin__hadoop-2.0.4-alpha/lib/