eabase

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggerganov/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

NOTE

These are NOT product / license keys that are valid for Windows activation.
These keys only select the edition of Windows to install during setup, but they do not activate or license the installation.

Index

Windows 11
RTM Generic Keys

I was wondering why it took so long for my deep learning rig to fully boot up. It literally takes 5 minutes to go from reboot to ssh service start. Unlike desktop motherboards, the ROMED8-2T has two 10G RDMA ethernet controllers and a port for the IPMI interface.

For a while I thought I must have done something wrong - but it turns out when there are free, unmapped ports it will block boot. To fix this, you just need to make the other interfaces optional in your /etc/netplan/*.yaml

network:
  ethernets:
    enoXnpX:
      addresses:
 - ...

	import torch
	import torch.nn as nn
	import torch.optim as optim
	import gym
	import numpy as np
	import pickle

	# Hyperparameters
	H = 200 # Number of hidden layer neurons
	batch_size = 10 # Every how many episodes to do a param update?

	$erroractionpreference = 'stop'

	$releases = 'https://files.lhmouse.com/nano-win/'

	ri -r -fo ~/Downloads/nano-installer -ea ignore
	mkdir ~/Downloads/nano-installer \| out-null
	pushd ~/Downloads/nano-installer
	curl -sLO ($releases + (
	iwr -usebasicparsing $releases \| % links \|
	? href -match '\.7z$' \| select -last 1 \| % href

	""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
	import numpy as np
	import pickle
	import gym

	# hyperparameters
	H = 200 # number of hidden layer neurons
	batch_size = 10 # every how many episodes to do a param update?
	learning_rate = 1e-4
	gamma = 0.99 # discount factor for reward

	# References :
	# - https://stackoverflow.com/questions/61776425/logic-for-real-time-algo-trading-expert

	import pytz
	import pandas as pd
	import MetaTrader5 as mt5
	import time
	from datetime import datetime
	from threading import Timer

	<#

	Prerequisites: PowerShell version 2 or above.
	License: MIT
	Author: Michael Klement <[email protected]>

	DOWNLOAD, from PowerShell version 3 or above:

	irm https://gist.github.com/mklement0/243ea8297e7db0e1c03a67ce4b1e765d/raw/Out-HostColored.ps1 \| iex

	<#

	Prerequisites: PowerShell v3+
	License: MIT
	Author: Michael Klement <[email protected]>

	DOWNLOAD and DEFINITION OF THE FUNCTION:

	irm https://gist.github.com/mklement0/25694cbb8e10a7044b36a310e1243959/raw/Get-CharInfo.ps1 \| iex

	<#
	.SYNOPSIS

	Speak text using SSML

	.DESCRIPTION

	Speak text using SSML, using built in MS speech synthesis. Will output metadata about result, including any embedded <mark>s

	.PARAMETER Text