k8si

#!/bin/bash

memory="1024m"
jarfile="/home/kate/research/myproject/grobid/grobid-core/target/grobid-core-0.3.4-SNAPSHOT.one-jar.jar"
grobidHome="/home/kate/research/myproject/grobid/grobid-home"
config="/home/kate/research/myproject/grobid/grobid-home/config/grobid.properties"
input="/home/kate/research/myproject/pdfs"
output="/home/kate/research/myproject/output"

java -Xmx$memory -jar $jarfile \

k8si

  def createParagraph2(paragraphNode: Node, paragraphStart: Int, doc: Document): Unit = {
    for (child <- paragraphNode.childNodes) {
      if (child.isInstanceOf[TextNode]) {
        val tmpDoc = new Document(child.asInstanceOf[TextNode].text)
        cc.factorie.app.nlp.segment.DeterministicNormalizingTokenizer.process(tmpDoc)
        //attach the tokens to the original document
        tmpDoc.tokens.foreach { token => new Token(doc, token.string) }
      } else if (child.nodeName.equals("a")) {
        val linkTarget: String = child.attr("href")
        val linkText: String = child.childNode(0).toString()

k8si

import java.io._

object TestStuff {

  class Person(val name: String) extends Serializable {
    var age: Int = 0
    object personProperties extends Serializable {
      val location: String = "MA"
      var job: String = ""
    }

k8si

import java.io._
import cc.factorie.app.nlp.Document

object TestStuff {
  def serializeStuff(): Unit = {

    class Thing(s: String) extends Serializable {
      override def toString: String = s"Thing($s)"
    }

k8si

class TestCategoricalDomain extends JUnitSuite with cc.factorie.util.FastLogging {

  @Test
  def testPlusEquals(): Unit = {

    val domain = new CategoricalDomain[String](List("yes", "no"))
    domain.freeze()
    printDomainInfo(domain, "init")
    /*
    init:

k8si

import logging
import traceback
from copy import deepcopy
from pathlib import Path

from transformers import PreTrainedTokenizer
from transformers.data.processors.squad import SquadV2Processor, SquadExample
from transformers.tokenization_bert import BertTokenizer
from transformers.tokenization_bert import BertTokenizerFast
from transformers.tokenization_gpt2 import GPT2Tokenizer, GPT2TokenizerFast

k8si

CMPSCI 630 Project 1

Useful Links

General Interpreters

• How to Write A Lisp Interpreter In Python
• paper on the Smalltalk bytecode interpreter

Python Interpreter

k8si

Notes about homing pigeons

• What were homing pigeons used for? Since homing pigeons can find their way home over very long distances, they were used to carry messages.
• How does the 'homing instinct' work? Via magnetoreception, or by sensing the Earth's magentic field. Essentially, homing pigeons have a built-in, biological compass. Scientists are not sure how this actually works.
• Does weather affect homing pigeons' ability to deliver messages? Yes. Bad weather affecting sky conditions can slow homing pigeons down. They have been found to be slow when the sky is grey with a low ceiling and high humidity.
• When do homing pigeons molt? They should molt once per year. When they're unmated, they usually molt beginning in May or June. If they're mated, they'll start molting about 1 week after the second set of eggs has been laid in the new season. Pigeons should be allowed to rest while they're molting, as it places a lot of physical strain on them.
• How do homing pigeons carry messages? If you have a me

k8si

#!/bin/bash
#
# Script requires:
# - python3 (tested with 3.11)
# - wget
#
# How to run:
#  $ git clone git@github.com:Mozilla-Ocho/llamafile.git && cd llamafile
#  $ wget <url of this gist>
#  $ ./test-llamafile-commit-with-minilm.sh <commit hash>