mrchainhead chainhead

Instructions

Set pull token and login with docker using the following command

$env:CR_PAT = "your_token"
$env:CR_PAT | docker login ghcr.io -u USERNAME --password-stdin

In launch/conf/platform.env, uncomment and set KAFKA_TAG=7.7.0

Notebook

Theory

LLM

Build LLM from scratch in Python using createllm package - https://pythonscholar.com/build-a-large-language-model-from-scratch/
Private LLM using databricks-dolly-15k (approximately 15,000 instruction/response fine-tuning records) - https://www.leewayhertz.com/build-private-llm/
The Emergence Of Large Language Model (LLM) API Build Frameworks - https://cobusgreyling.medium.com/the-emergence-of-large-language-model-llm-api-build-frameworks-78d83d68eeda
Corpus size and LLM - https://genai.stackexchange.com/q/613/2269

Person:

What is Generative AI?

ChatGPT:

Generative AI refers to a subset of artificial intelligence (AI) techniques and models that are designed to generate new, original content or data that resembles human-created content. These models are capable of producing text, images, audio, and even other forms of data, often with a high degree of creativity and realism. Generative AI has made significant advancements in recent years, thanks in part to deep learning and neural network architectures.

One of the most prominent types of generative AI models is the Generative Adversarial Network (GAN), introduced by Ian Goodfellow and his colleagues in 2014. GANs consist of two neural networks, a generator and a discriminator, which work in opposition to each other. The generator tries to create content that is indistinguishable from real data, while the discriminator tries to differentiate between real and generated data. This adversarial process helps the generator improve its output over time.

Applications o

Install NodeJs

curl -sL https://deb.nodesource.com/setup_16.x -o nodesource_setup.sh
sudo bash nodesource_setup.sh
sudo apt-get install nodejs -y

Install Docker

Introduction

This is a sample Websocket client to send random JSON payload to a Websockets server.

Installation

After cloning this gist, run the following commands.

npm init -y

Introduction

# https://raw.githubusercontent.com/eclipse/mosquitto/master/mosquitto.conf
kubectl create ns/mqtt
kubectl -n mqtt create configmap mosquitto-conf --from-file=mosquitto.conf
kubectl -n mqtt create -f deploy.yaml

Introduction

A basic implementation of logging with Go language. Copied from https://www.honeybadger.io/blog/golang-logging/

Usage

Run the following commands to test with built-in log package. Logs will be saved in logs.txt.

go run log.go

Introduction

This gist shows a basic implementation of a HTTP server that handles the request to upgrade connection to Websockets.

Introduction

This is a short description of how to get git credentials in an EC2 instance set-up for CI/CD scripts. In the following scripts, we do the following:

Install the AWS CLI. See here for description of steps on Linux.
Install jq to parse the JSON output from CLI.
Run the aws CLI for ssm (AWS Systems Manager) to extract parameter values for git user.
Set the git user name globally.
Set the name of the script in GIT_ASKPASS that will return the git password.

	#!/usr/bin/python
	import RPi.GPIO as GPIO
	import time

	#GPIO SETUP
	channel = 21
	GPIO.setmode(GPIO.BCM)
	GPIO.setup(channel, GPIO.IN)

	def moisture_detect(channel):