Omkarnath Omie

This worked on 14/May/23. The instructions will probably require updating in the future.

llama is a text prediction model similar to GPT-2, and the version of GPT-3 that has not been fine tuned yet. It is also possible to run fine tuned versions (like alpaca or vicuna with this. I think. Those versions are more focused on answering questions)

Note: I have been told that this does not support multiple GPUs. It can only use a single GPU.

It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.

Clone llama.cpp from git, I am on commit 08737ef720f0510c7ec2aa84d7f70c691073c35d.

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

Neo4j Tutorial

Fundamentals

Store any kind of data using the following graph concepts:

Node: Graph data records
Relationship: Connect nodes (has direction and a type)
Property: Stores data in key-value pair in nodes and relationships
Label: Groups nodes and relationships (optional)

Credit goes to

Jan Klaas Kollhof (and Fred Benenson)
Chris Skardon

Installation

Since the original plugin has been developed for Sublime Text 2 we have to install it manually.

Go to https://github.com/fredbenenson/sublime-cypher, download ZIP of the repo, extract the content and rename the folder to ‘Cypher’. You can download the original repo from https://github.com/kollhof/sublime-cypher but Fred Benenson introduced a handy fix for UTF-8 data, which hasn't integrated at the point of this writing.

	package main

	import "database/sql"
	import (
	"fmt"
	_ "github.com/go-sql-driver/mysql"
	"github.com/satori/go.uuid"
	"math/rand"
	"sync"
	)

	# LVDB - LLOOGG Memory DB
	# Copyriht (C) 2009 Salvatore Sanfilippo <[email protected]>
	# All Rights Reserved

	# TODO
	# - cron with cleanup of timedout clients, automatic dump
	# - the dump should use array startsearch to write it line by line
	# and may just use gets to read element by element and load the whole state.
	# - 'help','stopserver','saveandstopserver','save','load','reset','keys' commands.
	# - ttl with milliseconds resolution 'ttl a 1000'. Check ttl in dump!

	#!/usr/bin/env perl

	use strict;
	use warnings;

	use AnyEvent;
	use AnyEvent::Handle;
	use AnyEvent::Impl::EV;
	use AnyEvent::Socket qw/tcp_connect/;
	use InfluxDB::LineProtocol qw/data2line/;

	// If "const" is to the LEFT of "*" it applies to the object being pointed at
	// If "const" is to the RIGHT of "*" it applies to the variable holding the pointer address

	const T* ptr; // object is immutable
	T const* ptr; // "

	T* const ptr; // 'ptr' cannot be changed to point to a different address, but object is not immutable
	// (i.e. the variable is const, not the thing it points to)

	const T* const ptr; // object is immutable AND 'ptr' cannot be changed to point to a different address

	// Usage:
	// Copy and paste all of this into a debug console window of the "Who is Hiring?" comment thread
	// then use as follows:
	//
	// query(term \| [term, term, ...], term \| [term, term, ...], ...)
	//
	// When arguments are in an array then that means an "or" and when they are seperate that means "and"
	//
	// Term is of the format:
	// ((-)text/RegExp) ( '-' means negation )

	#include <stdio.h>
	#include <stdlib.h>
	#include <string.h>

	int addi(int a, int b) {
	return a + b;
	}

	char adds(char a, char *b) {
	char *res = malloc(strlen(a) + strlen(b) + 1);