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

karpathy

"""
stable diffusion dreaming
creates hypnotic moving videos by smoothly walking randomly through the sample space

example way to run this script:

$ python stablediffusionwalk.py --prompt "blueberry spaghetti" --name blueberry

to stitch together the images, e.g.:
$ ffmpeg -r 10 -f image2 -s 512x512 -i blueberry/frame%06d.jpg -vcodec libx264 -crf 10 -pix_fmt yuv420p blueberry.mp4

unkn-one

import logging

import cv2
import PySpin

logger = logging.getLogger(__name__)


class Camera(object):
    def __init__(self, cam):

bkozora

# Automated AMI Backups
#
# @author Bobby Kozora
#
# This script will search for all instances having a tag with the name "backup"
# and value "Backup" on it. As soon as we have the instances list, we loop
# through each instance
# and create an AMI of it. Also, it will look for a "Retention" tag key which
# will be used as a retention policy number in days. If there is no tag with
# that name, it will use a 7 days default value for each AMI.

karpathy

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)