thomwolf

import os; import psutil; import timeit
from datasets import load_dataset

mem_before = psutil.Process(os.getpid()).memory_info().rss >> 20
wiki = load_dataset("wikipedia", "20200501.en", split='train')
mem_after = psutil.Process(os.getpid()).memory_info().rss >> 20
print(f"RAM memory used: {(mem_after - mem_before)} MB")

s = """batch_size = 1000
for i in range(0, len(wiki), batch_size):

jinglescode

import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import TransformerEncoder, TransformerEncoderLayer


class TransformerModel(nn.Module):

    def __init__(self, ntoken, ninp, nhead, nhid, nlayers, dropout=0.5):

aditya-malte

seanjtaylor

VarunVats9

import java.util.SortedMap;
import java.util.TreeMap;

public class ConsistentHashing {

    // Consistent Hashing with Ring having 50 buckets.
    final static int LIMIT = 50;

    // Sorted Map.
    final static SortedMap<Integer, String> bucketIdToServer = new TreeMap<>();

kaustubhn

# Implementation of a chinese restaurant process function for a given list of word vectors.
def crp(vecs):
    clusterVec = [[0.0] * 25]         # tracks sum of vectors in a cluster
    clusterIdx = [[]]        # array of index arrays. e.g. [[1, 3, 5], [2, 4, 6]]
    ncluster = 0
    # probablity to create a new table if new customer
    # is not strongly "similar" to any existing table
    pnew = 1.0/ (1 + ncluster)  
    N = len(vecs)
    rands = [random.random() for x in range(N)]         # N rand variables sampled from U(0, 1)

max-mapper

{"help": "https://catalog.data.gov/api/3/action/help_show?name=package_search", "success": true, "result": {"count": 48, "sort": "views_recent desc", "facets": {}, "results": [{"license_title": "License not specified", "maintainer": "New Media", "relationships_as_object": [], "private": false, "maintainer_email": "newmedia@whitehouse.gov", "num_tags": 5, "id": "59694770-b6b6-4ae0-a4b9-4ae69c0be2f6", "metadata_created": "2016-07-02T10:06:26.199575", "metadata_modified": "2016-07-02T10:06:26.199575", "author": null, "author_email": null, "state": "active", "version": null, "creator_user_id": "47303a9e-1187-4290-85a3-1fc02dc49e4a", "type": "dataset", "resources": [{"cache_last_updated": null, "package_id": "59694770-b6b6-4ae0-a4b9-4ae69c0be2f6", "webstore_last_updated": null, "id": "3a8a0ad1-19e7-4153-bb2f-d70cf88aaaf8", "size": null, "state": "active", "hash": "", "description": "", "format": "CSV", "tracking_summary": {"total": 32, "recent": 1}, "last_modified": null, "url_type": null, "no_real_name": "True", 

kuboosoft

<?xml version="1.0" encoding="UTF-8"?>
<!--
# Goes inside %APPDATA%\kodi\userdata
-->
<playercorefactory>
<players>
<player name="VLC" type="ExternalPlayer" audio="false" video="true">
<filename>/usr/bin/vlc</filename>
<hidexbmc>true</hidexbmc>
<hideconsole>true</hideconsole>

kn9ts

GPL3 LICENSE SYNOPSIS

TL;DR* Here's what the license entails:

1. Anyone can copy, modify and distribute this software.
2. You have to include the license and copyright notice with each and every distribution.
3. You can use this software privately.
4. You can use this software for commercial purposes.
5. If you dare build your business solely from this code, you risk open-sourcing the whole code base.

vasanthk

System Design Cheatsheet

Picking the right architecture = Picking the right battles + Managing trade-offs

Basic Steps

1. Clarify and agree on the scope of the system

• User cases (description of sequences of events that, taken together, lead to a system doing something useful)
  • Who is going to use it?
  • How are they going to use it?