ddmitov

import os
import json

def lambda_handler(event, context):
    json_region = os.environ['AWS_REGION']

    return {
        "statusCode": 200,
        "headers": {
            "Content-Type": "application/json"

ddmitov

Free Datasets

• https://www.kaggle.com/datasets/benjaminawd/new-york-times-articles-comments-2020 - 2GB
• https://www.kaggle.com/datasets/gufukuro/movie-scripts-corpus - 689MB
• https://www.nyc.gov/site/tlc/about/tlc-trip-record-data.page - New York Taxi Trip Record Data

Free Compute

• https://linux-blog.anracom.com/2023/05/04/google-colab-ram-vram-and-gpu-usage-limits-i-no-clear-conditions-over-multiple-sessions/
• https://towardsdatascience.com/using-kaggle-for-your-data-science-work-a2e78d692395
• https://huggingface.co/docs/hub/spaces-overview
• https://saturncloud.io/plans/saturn_cloud_plans/

ddmitov

#!/bin/sh

gs	-q -dNOPAUSE -dBATCH -dSAFER \
	-sDEVICE=pdfwrite \
	-dCompatibilityLevel=1.3 \
	-dPDFSETTINGS=/screen \
	-dEmbedAllFonts=true \
	-dSubsetFonts=true \
	-dColorImageDownsampleType=/Bicubic \
	-dColorImageResolution=72 \

ddmitov

#!/usr/bin/env bash

# This script demonstrates deterministic output from llama.cpp.
# Place it in an empty directory, run it and it will:
# 1. Clone llama.cpp
# 2. Build llama-cli, it takes a few minutes
# 3. Download a small model
# 4. Run the same prompt twice with the same settings
# 5. Compare the outputs and print whether they are identical