Discover gists

LLM Samplers Explained

Everytime a large language model makes predictions, all of the thousands of tokens in the vocabulary are assigned some degree of probability, from almost 0%, to almost 100%. There are different ways you can decide to choose from those predictions. This process is known as "sampling", and there are various strategies you can use which I will cover here.

OpenAI Samplers

Temperature

Temperature is a way to control the overall confidence of the model's scores (the logits). What this means is that, if you use a lower value than 1.0, the relative distance between the tokens will become larger (more deterministic), and if you use a larger value than 1.0, the relative distance between the tokens becomes smaller (less deterministic).
1.0 Temperature is the original distribution that the model was trained to optimize for, since the scores remain the same.
Graph demonstration with voiceover: https://files.catbox.moe/6ht56x.mp4

Problem

Begin with VStack that contain texts as children.

struct TestView: View {
    
    var body: some View {
        VStack(alignment: .trailing) {
            Text("Hello, World!")

Hexadecimal color code for transparency

How to set transparency with hex value ?

For example, you want to set 40% alpha transparence to #000000 (black color), you need to add 66 like this #66000000.

Download This sample on Google Play Store

Session Open Group Directory

AI/ML Toolkit

Some notes on AI/ML tools that seem interesting/useful (largely aiming to focus on open source tools)

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

	esphome:
	name: esp32-mic-speaker
	friendly_name: esp32-mic-speaker
	on_boot:
	- priority: -100
	then:
	- wait_until: api.connected
	- delay: 1s
	- if:
	condition:

	# TODO: Verify to link statically some dependencies usually not available in a default instllation of RHEL/CentOS (ex.: libxcb)

	###################
	## Configuration ##
	###################

	FFMPEG_CPU_COUNT=$(nproc)
	FFMPEG_ENABLE="--enable-gpl --enable-version3 --enable-nonfree --enable-runtime-cpudetect --enable-gray --enable-openssl --enable-libfreetype"
	FFMPEG_HOME=/usr/local/src/ffmpeg

	VMware vSphere 6 Enterprise Plus
	1C20K-4Z214-H84U1-T92EP-92838
	1A2JU-DEH12-48460-CT956-AC84D
	MC28R-4L006-484D1-VV8NK-C7R58
	5C6TK-4C39J-48E00-PH0XH-828Q4
	4A4X0-69HE3-M8548-6L1QK-1Y240

	VMware vSphere with Operations Management 6 Enterprise
	4Y2NU-4Z301-085C8-M18EP-2K8M8
	1Y48R-0EJEK-084R0-GK9XM-23R52

	# Source: https://gist.github.com/c7cdfef142bd65cc744789d3c1e90170

	###########################################
	# Talos Linux: OS Designed For Kubernetes #
	# https://youtu.be/iEFb2Zg4xUg #
	###########################################

	# Additional Info:
	# - Talos Linux: https://www.talos.dev/
	# - How To Create, Provision, And Operate Kubernetes With Cluster API (CAPI): https://youtu.be/8yUDUhZ6ako