GPT-3, GPT-J og GPT-NeoX er svært kraftige AI-modeller. Vi viser deg her hvordan du effektivt kan bruke disse modellene takket være "few-shot learning". Few-shot-læring er som å trene / finjustere en AI-modell ved ganske enkelt å gi et par eksempler i ledeteksten.
GPT-3, utgitt av OpenAI, er den kraftigste AI-modellen som noensinne er utgitt for tekstforståelse og tekstgenerering.
Den ble trent på 175 milliarder parametere, noe som gjør den ekstremt allsidig og i stand til å forstå stort sett hva som helst!
Du kan gjøre alle slags ting med GPT-3 som chatbots, innholdsoppretting, enhetsuttrekk, klassifisering, oppsummering og mye mer. Men det krever litt øvelse, og det er ikke lett å bruke denne modellen riktig.
GPT-NeoX og GPT-J er begge modeller for naturlig språkbehandling med åpen kildekode, laget av et kollektiv av forskere som arbeider med kunstig intelligens. forskere som arbeider med åpen kildekode for kunstig intelligens (se EleutherAIs nettsted).
GPT-J har 6 milliarder parametere og GPT-NeoX har 20 milliarder parametere, noe som gjør dem til de mest avanserte åpen kildekode-modellene for Natural Language Processing modeller i skrivende stund. De er direkte alternativer til OpenAIs proprietære GPT-3 Curie.
Disse modellene er svært allsidige. De kan brukes til nesten alle bruksområder for naturlig språkbehandling: tekstgenerering, analyse av følelser analyse, klassifisering, maskinoversettelse, ... og mye mer (se nedenfor). Men å bruke dem effektivt noen ganger krever øvelse. Deres responstid (latenstid) kan også være lengre enn mer standard Natural Language Processing modeller for naturlig språkbehandling.
GPT-J og GPT-NeoX er begge tilgjengelige på NLP Cloud API. Nedenfor viser vi deg eksempler som er oppnådd
ved hjelp av
GPT-J-endepunktet til NLP Cloud på GPU, med Python-klienten. Hvis du vil kopiere og lime inn eksemplene,
vennligst
ikke glem å legge til ditt eget API-token. For å installere Python-klienten må du først kjøre følgende: pip install nlpcloud.
Few-shot learning handler om å hjelpe en maskinlæringsmodell med å lage prediksjoner takket være bare et par få eksempler. Ingen grunn til å trene en ny modell her: modeller som GPT-3, GPT-J og GPT-NeoX er så store at de kan enkelt kan tilpasse seg mange sammenhenger uten å måtte læres opp på nytt.
Å gi bare noen få eksempler til modellen bidrar til å øke nøyaktigheten dramatisk.
I Natural Language Processing er ideen å sende disse eksemplene sammen med tekstinput. Se eksemplene nedenfor!
Vær også oppmerksom på at hvis det ikke er nok å lære med få skudd, kan du også finjustere GPT-3 på OpenAIs nettsted og GPT-J på NLP Cloud slik at modellen er perfekt skreddersydd for ditt brukstilfelle.
Du kan enkelt teste læring med få skudd på NLP Cloud Playground, i tekstgenereringsdelen. Klikk her for å prøve tekstgenerering på Playground. Da er det bare å bruke et av eksemplene nedenfor i denne artikkelen og se selv.
Eksempel på generering av tweets på NLP Cloud Playground
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Message: Support has been terrible for 2 weeks...
Sentiment: Negative
###
Message: I love your API, it is simple and so fast!
Sentiment: Positive
###
Message: GPT-J has been released 2 months ago.
Sentiment: Neutral
###
Message: The reactivity of your team has been amazing, thanks!
Sentiment:""",
min_length=1,
max_length=1,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
Positive
Som du kan se, det faktum at vi først gir 3 eksempler med et riktig format, fører GPT-J til å forstå at vi ønsker å utføre sentimentanalyse. Og resultatet er bra.
Du kan hjelpe GPT-J med å forstå de forskjellige
seksjonene ved å bruke et egendefinert skilletegn som det følgende: ###. Vi kunne godt trenge noe annet som dette: ---. Eller rett og slett en ny
linje. Deretter angir vi "end_sequence", som er en NLP Cloud-parameter som
forteller GPT-J å slutte å generere innhold etter en ny linje. + ###: end_sequence="###".
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""description: a red button that says stop
code: <button style=color:white; background-color:red;>Stop</button>
###
description: a blue box that contains yellow circles with red borders
code: <div style=background-color: blue; padding: 20px;><div style=background-color: yellow; border: 5px solid red; border-radius: 50%; padding: 20px; width: 100px; height: 100px;>
###
description: a Headline saying Welcome to AI
code:""",
max_length=500,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
<h1 style=color: white;>Welcome to AI</h1>
Kodegenerering med GPT-J er virkelig fantastisk. Dette er delvis takket være det faktum at GPT-J har blitt trent på enorme kodebaser.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Question: Fetch the companies that have less than five people in it.
Answer: SELECT COMPANY, COUNT(EMPLOYEE_ID) FROM Employee GROUP BY COMPANY HAVING COUNT(EMPLOYEE_ID) < 5;
###
Question: Show all companies along with the number of employees in each department
Answer: SELECT COMPANY, COUNT(COMPANY) FROM Employee GROUP BY COMPANY;
###
Question: Show the last record of the Employee table
Answer: SELECT * FROM Employee ORDER BY LAST_NAME DESC LIMIT 1;
###
Question: Fetch three employees from the Employee table;
Answer:""",
max_length=100,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
SELECT * FROM Employee ORDER BY ID DESC LIMIT 3;
Automatisk generering av SQL fungerer svært godt med GPT-J, spesielt på grunn av SQLs deklarative natur, og det faktum at SQL er et ganske begrenset språk med relativt få muligheter (sammenlignet med de fleste programmeringsspråk). programmeringsspråk).
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""[Text]: Fred is a serial entrepreneur. Co-founder and CEO of Platform.sh, he previously co-founded Commerce Guys, a leading Drupal ecommerce provider. His mission is to guarantee that as we continue on an ambitious journey to profoundly transform how cloud computing is used and perceived, we keep our feet well on the ground continuing the rapid growth we have enjoyed up until now.
[Name]: Fred
[Position]: Co-founder and CEO
[Company]: Platform.sh
###
[Text]: Microsoft (the word being a portmanteau of "microcomputer software") was founded by Bill Gates on April 4, 1975, to develop and sell BASIC interpreters for the Altair 8800. Steve Ballmer replaced Gates as CEO in 2000, and later envisioned a "devices and services" strategy.
[Name]: Steve Ballmer
[Position]: CEO
[Company]: Microsoft
###
[Text]: Franck Riboud was born on 7 November 1955 in Lyon. He is the son of Antoine Riboud, the previous CEO, who transformed the former European glassmaker BSN Group into a leading player in the food industry. He is the CEO at Danone.
[Name]: Franck Riboud
[Position]: CEO
[Company]: Danone
###
[Text]: David Melvin is an investment and financial services professional at CITIC CLSA with over 30 years’ experience in investment banking and private equity. He is currently a Senior Adviser of CITIC CLSA.
""",
top_p=0,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
[Name]: David Melvin
[Position]: Senior Adviser
[Company]: CITIC CLSA
Som du kan se, er GPT-J veldig god til å trekke ut strukturerte data fra ustrukturert tekst. Dette er virkelig imponerende hvordan GPT-J løser entitetsekstraksjon uten at det er nødvendig med ny opplæring! Vanligvis å trekke ut nye typer entiteter (som navn, stilling, land osv.) krever en helt ny prosess med annotasjon, opplæring, distribusjon.... Her er det helt sømløst.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Context: NLP Cloud was founded in 2021 when the team realized there was no easy way to reliably leverage Natural Language Processing in production.
Question: When was NLP Cloud founded?
Answer: 2021
###
Context: NLP Cloud developed their API by mid-2020 and they added many pre-trained open-source models since then.
Question: What did NLP Cloud develop?
Answer: API
###
Context: All plans can be stopped anytime. You only pay for the time you used the service. In case of a downgrade, you will get a discount on your next invoice.
Question: When can plans be stopped?
Answer: Anytime
###
Context: The main challenge with GPT-J is memory consumption. Using a GPU plan is recommended.
Question: Which plan is recommended for GPT-J?
Answer:""",
min_length=1,
max_length=20,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
GPU-plan
Svar på spørsmål fungerer veldig bra. Det kan også oppnås med andre dedikerte modeller for naturlig språkbehandling, men kanskje ikke på samme måte. kanskje ikke med samme grad av nøyaktighet.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Here is a tutorial about how to make a cake.
1. Take some flour.
2. Take some sugar.""",
max_length=500)
print(generation["generated_text"])
Produksjon:
Here is a tutorial how to make a cake.
1. Take some flour.
2. Take some sugar.
3. Take some butter.
4. Take some eggs.
5. Take some water.
6. Take some baking powder.
7. Take some vanilla.
8. Mix all together.
9. Bake in a pan.
10. Enjoy.
Well, that's it. You can make this for your birthday or a party or you can even make it for your kids. They will love this.
Som du kan se, er det ganske imponerende hvordan GPT-J automatisk følger din opprinnelige formatering, og det generert innhold er også veldig bra også. Du kan lage en skikkelig kake ut av dette (ikke prøvd ennå). skjønt).
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""I love goin to the beach.
Correction: I love going to the beach.
###
Let me hav it!
Correction: Let me have it!
###
It have too many drawbacks.
Correction: It has too many drawbacks.
###
I do not wan to go
Correction:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
Jeg vil ikke dra.
Stave- og grammatikkrettinger fungerer som forventet. Hvis du vil være mer spesifikk om plasseringen av feilen i setningen, kan det være lurt å bruke en egen feilen i setningen, kan det være lurt å bruke en egen modell.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Hugging Face a révolutionné le NLP.
Translation: Hugging Face revolutionized NLP.
###
Cela est incroyable!
Translation: This is unbelievable!
###
Désolé je ne peux pas.
Translation: Sorry but I cannot.
###
NLP Cloud permet de deployer le NLP en production facilement.
Translation:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
NLP Cloud makes it easy to deploy NLP to production.
Maskinoversettelse krever vanligvis egne modeller (ofte én per språk). Her håndteres alle språkene ut av boksen av GPT-J, noe som er ganske imponerende.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""keyword: markets
tweet: Take feedback from nature and markets, not from people
###
keyword: children
tweet: Maybe we die so we can come back as children.
###
keyword: startups
tweet: Startups should not worry about how to put out fires, they should worry about how to start them.
###
keyword: NLP
tweet:""",
max_length=200,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
People want a way to get the benefits of NLP without paying for it.
Her er en morsom og enkel måte å generere korte tweets etter en kontekst.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""This is a discussion between a [human] and a [robot].
The [robot] is very nice and empathetic.
[human]: Hello nice to meet you.
[robot]: Nice to meet you too.
###
[human]: How is it going today?
[robot]: Not so bad, thank you! How about you?
###
[human]: I am ok, but I am a bit sad...
[robot]: Oh? Why that?
###
[human]: I broke up with my girlfriend...
[robot]:""",
min_length=1,
max_length=20,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
Oh? How did that happen?
Som du kan se, forstår GPT-J riktig at du er i samtalemodus. Og det veldig kraftige tingen er at hvis du endrer tonen i konteksten din, vil svarene fra modellen følge det samme tone (sarkasme, sinne, nysgjerrighet ...).
Vi skrev faktisk en egen bloggartikkel om hvordan du bygger en chatbot med GPT-3/GPT-J, Les den gjerne!
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""I want to start coding tomorrow because it seems to be so fun!
Intent: start coding
###
Show me the last pictures you have please.
Intent: show pictures
###
Search all these files as fast as possible.
Intent: search files
###
Can you please teach me Chinese next week?
Intent:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
learn chinese
Dette er ganske imponerende hvordan GPT-J kan oppdage intensjonen fra setningen din. Det fungerer veldig bra for mer komplekse setninger. Du kan til og med be den om å å formatere hensikten annerledes hvis du vil. Du kan for eksempel automatisk generere et Javascript funksjonsnavn som "learnChinese".
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""[Original]: Algeria recalled its ambassador to Paris on Saturday and closed its airspace to French military planes a day later after the French president made comments about the northern Africa country.
[Paraphrase]: Last Saturday, the Algerian government recalled its ambassador and stopped accepting French military airplanes in its airspace. It happened one day after the French president made comments about Algeria.
###
[Original]: President Macron was quoted as saying the former French colony was ruled by a "political-military system" with an official history that was based not on truth, but on hatred of France.
[Paraphrase]: Emmanuel Macron said that the former colony was lying and angry at France. He also said that the country was ruled by a "political-military system".
###
[Original]: The diplomatic spat came days after France cut the number of visas it issues for citizens of Algeria and other North African countries.
[Paraphrase]: Diplomatic issues started appearing when France decided to stop granting visas to Algerian people and other North African people.
###
[Original]: After a war lasting 20 years, following the decision taken first by President Trump and then by President Biden to withdraw American troops, Kabul, the capital of Afghanistan, fell within a few hours to the Taliban, without resistance.
[Paraphrase]:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True,
min_length=0,
max_length=50)
print(generation["generated_text"])
Produksjon:
French President Emmanuel Macron hopes the diplomatic tension with Algeria will calm down. He wants to make progress in the relations with the former French colony. President Macron says he has a good relationship with his Algerian counterpart and he is glad that they have a cordial relationship. The president was quoted as saying that Algeria was ruled by a "political-military system" with an official history that was based not on truth, but on hatred of France. France cut the number of visas it issues for citizens of Algeria and other North African countries.
GPT-J gjorde endringer i avsnittet vårt, samtidig som de beholdt hovedinnholdet, som er det som parafrasering handler om. Du kan perfekt oppmuntre GPT-J til å returnere mer originale omskrivninger ved å sende forskjellige eksempler i input, og ved å leke med API-parametere som temperatur, top_p, repetisjonsstraff...
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""[Original]: America has changed dramatically during recent years. Not only has the number of graduates in traditional engineering disciplines such as mechanical, civil, electrical, chemical, and aeronautical engineering declined, but in most of the premier American universities engineering curricula now concentrate on and encourage largely the study of engineering science. As a result, there are declining offerings in engineering subjects dealing with infrastructure, the environment, and related issues, and greater concentration on high technology subjects, largely supporting increasingly complex scientific developments. While the latter is important, it should not be at the expense of more traditional engineering.
Rapidly developing economies such as China and India, as well as other industrial countries in Europe and Asia, continue to encourage and advance the teaching of engineering. Both China and India, respectively, graduate six and eight times as many traditional engineers as does the United States. Other industrial countries at minimum maintain their output, while America suffers an increasingly serious decline in the number of engineering graduates and a lack of well-educated engineers.
(Source: Excerpted from Frankel, E.G. (2008, May/June) Change in education: The cost of sacrificing fundamentals. MIT Faculty
[Summary]: MIT Professor Emeritus Ernst G. Frankel (2008) has called for a return to a course of study that emphasizes the traditional skills of engineering, noting that the number of American engineering graduates with these skills has fallen sharply when compared to the number coming from other countries.
###
[Original]: So how do you go about identifying your strengths and weaknesses, and analyzing the opportunities and threats that flow from them? SWOT Analysis is a useful technique that helps you to do this.
What makes SWOT especially powerful is that, with a little thought, it can help you to uncover opportunities that you would not otherwise have spotted. And by understanding your weaknesses, you can manage and eliminate threats that might otherwise hurt your ability to move forward in your role.
If you look at yourself using the SWOT framework, you can start to separate yourself from your peers, and further develop the specialized talents and abilities that you need in order to advance your career and to help you achieve your personal goals.
[Summary]: SWOT Analysis is a technique that helps you identify strengths, weakness, opportunities, and threats. Understanding and managing these factors helps you to develop the abilities you need to achieve your goals and progress in your career.
###
[Original]: Jupiter is the fifth planet from the Sun and the largest in the Solar System. It is a gas giant with a mass one-thousandth that of the Sun, but two-and-a-half times that of all the other planets in the Solar System combined. Jupiter is one of the brightest objects visible to the naked eye in the night sky, and has been known to ancient civilizations since before recorded history. It is named after the Roman god Jupiter.[19] When viewed from Earth, Jupiter can be bright enough for its reflected light to cast visible shadows,[20] and is on average the third-brightest natural object in the night sky after the Moon and Venus.
Jupiter is primarily composed of hydrogen with a quarter of its mass being helium, though helium comprises only about a tenth of the number of molecules. It may also have a rocky core of heavier elements,[21] but like the other giant planets, Jupiter lacks a well-defined solid surface. Because of its rapid rotation, the planet's shape is that of an oblate spheroid (it has a slight but noticeable bulge around the equator).
[Summary]: Jupiter is the largest planet in the solar system. It is a gas giant, and is the fifth planet from the sun.
###
[Original]: For all its whizz-bang caper-gone-wrong energy, and for all its subsequent emotional troughs, this week’s Succession finale might have been the most important in its entire run. Because, unless I am very much wrong, Succession – a show about people trying to forcefully mount a succession – just had its succession. And now everything has to change.
The episode ended with Logan Roy defying his children by selling Waystar Royco to idiosyncratic Swedish tech bro Lukas Matsson. It’s an unexpected twist, like if King Lear contained a weird new beat where Lear hands the British crown to Jack Dorsey for a laugh, but it sets up a bold new future for the show. What will happen in season four? Here are some theories.
Season three of Succession picked up seconds after season two ended. It was a smart move, showing the immediate swirl of confusion that followed Kendall Roy’s decision to undo his father, and something similar could happen here. This week’s episode ended with three of the Roy siblings heartbroken and angry at their father’s grand betrayal. Perhaps season four could pick up at that precise moment, and show their efforts to reorganise their rebellion against him. This is something that Succession undoubtedly does very well – for the most part, its greatest moments have been those heart-thumping scenes where Kendall scraps for support to unseat his dad – and Jesse Armstrong has more than enough dramatic clout to centre the entire season around the battle to stop the Matsson deal dead in its tracks.
[Summary]:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True,
min_length=20,
max_length=200)
print(generation["generated_text"])
Produksjon:
Season 3 of Succession ended with Logan Roy trying to sell his company to Lukas Matsson.
Tekstoppsummering er en vanskelig oppgave. GPT-J er veldig god til dette, så lenge du gir den de riktige de riktige eksemplene. Størrelsen på sammendraget og tonen i sammendraget avhenger i stor grad av eksemplene du har laget. opprettet. Det er for eksempel ikke sikkert at du lager samme type eksempler, enten du prøver å lage et enkelt sammendrag for barn eller et avansert sammendrag. enkelt sammendrag for barn eller et avansert medisinsk sammendrag for leger. Hvis inndatastørrelsen til GPT-J er for liten for oppsummeringseksemplene dine, kan det være lurt å finjustere GPT-J for oppsummeringsoppgaven din.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Message: When the spaceship landed on Mars, the whole humanity was excited
Topic: space
###
Message: I love playing tennis and golf. I'm practicing twice a week.
Topic: sport
###
Message: Managing a team of sales people is a tough but rewarding job.
Topic: business
###
Message: I am trying to cook chicken with tomatoes.
Topic:""",
min_length=1,
max_length=5,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
food
Her er en enkel og effektiv måte å kategorisere et stykke tekst på takket være den såkalte "zero-shot læring" -teknikk, uten å måtte erklære kategorier på forhånd.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Information Retrieval (IR) is the process of obtaining resources relevant to the information need. For instance, a search query on a web search engine can be an information need. The search engine can return web pages that represent relevant resources.
Keywords: information, search, resources
###
David Robinson has been in Arizona for the last three months searching for his 24-year-old son, Daniel Robinson, who went missing after leaving a work site in the desert in his Jeep Renegade on June 23.
Keywords: searching, missing, desert
###
I believe that using a document about a topic that the readers know quite a bit about helps you understand if the resulting keyphrases are of quality.
Keywords: document, understand, keyphrases
###
Since transformer models have a token limit, you might run into some errors when inputting large documents. In that case, you could consider splitting up your document into paragraphs and mean pooling (taking the average of) the resulting vectors.
Keywords:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
paragraphs, transformer, input, errors
Søkeordsekstraksjon handler om å få de viktigste ideene fra et stykke tekst. Dette er et interessant Natural Language Processing underfelt som GPT-J kan håndtere veldig bra. Se nedenfor for utvinning av nøkkelord (det samme, men med flere ord). flere ord).
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Information Retrieval (IR) is the process of obtaining resources relevant to the information need. For instance, a search query on a web search engine can be an information need. The search engine can return web pages that represent relevant resources.
Keywords: information retrieval, search query, relevant resources
###
David Robinson has been in Arizona for the last three months searching for his 24-year-old son, Daniel Robinson, who went missing after leaving a work site in the desert in his Jeep Renegade on June 23.
Keywords: searching son, missing after work, desert
###
I believe that using a document about a topic that the readers know quite a bit about helps you understand if the resulting keyphrases are of quality.
Keywords: document, help understand, resulting keyphrases
###
Since transformer models have a token limit, you might run into some errors when inputting large documents. In that case, you could consider splitting up your document into paragraphs and mean pooling (taking the average of) the resulting vectors.
Keywords:""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
large documents, paragraph, mean pooling
Samme eksempel som ovenfor, bortsett fra at vi denne gangen ikke ønsker å trekke ut ett enkelt ord, men flere ord. (kalt nøkkelord).
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""Generate a product description out of keywords.
Keywords: shoes, women, $59
Sentence: Beautiful shoes for women at the price of $59.
###
Keywords: trousers, men, $69
Sentence: Modern trousers for men, for $69 only.
###
Keywords: gloves, winter, $19
Sentence: Amazingly hot gloves for cold winters, at $19.
###
Keywords: t-shirt, men, $39
Sentence:""",
min_length=5,
max_length=30,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
Extraordinary t-shirt for men, for $39 only.
Det er mulig å be GPT-J om å generere en produktbeskrivelse eller en annonse som inneholder spesifikke nøkkelord. Her genererer vi bare genererer vi bare en enkel setning, men vi kan enkelt generere et helt avsnitt om nødvendig.
import nlpcloud
client = nlpcloud.Client("gpt-j", "your_token", gpu=True)
generation = client.generation("""[Title]: 3 Tips to Increase the Effectiveness of Online Learning
[Blog article]: <h1>3 Tips to Increase the Effectiveness of Online Learning</h1>
<p>The hurdles associated with online learning correlate with the teacher’s inability to build a personal relationship with their students and to monitor their productivity during class.</p>
<h2>1. Creative and Effective Approach</h2>
<p>Each aspect of online teaching, from curriculum, theory, and practice, to administration and technology, should be formulated in a way that promotes productivity and the effectiveness of online learning.</p>
<h2>2. Utilize Multimedia Tools in Lectures</h2>
<p>In the 21st century, networking is crucial in every sphere of life. In most cases, a simple and functional interface is preferred for eLearning to create ease for the students as well as the teacher.</p>
<h2>3. Respond to Regular Feedback</h2>
<p>Collecting student feedback can help identify which methods increase the effectiveness of online learning, and which ones need improvement. An effective learning environment is a continuous work in progress.</p>
###
[Title]: 4 Tips for Teachers Shifting to Teaching Online
[Blog article]: <h1>4 Tips for Teachers Shifting to Teaching Online </h1>
<p>An educator with experience in distance learning shares what he’s learned: Keep it simple, and build in as much contact as possible.</p>
<h2>1. Simplicity Is Key</h2>
<p>Every teacher knows what it’s like to explain new instructions to their students. It usually starts with a whole group walk-through, followed by an endless stream of questions from students to clarify next steps.</p>
<h2>2. Establish a Digital Home Base</h2>
<p>In the spirit of simplicity, it’s vital to have a digital home base for your students. This can be a district-provided learning management system like Canvas or Google Classrooms, or it can be a self-created class website. I recommend Google Sites as a simple, easy-to-set-up platform.</p>
<h2>3. Prioritize Longer, Student-Driven Assignments</h2>
<p>Efficiency is key when designing distance learning experiences. Planning is going to take more time and require a high level of attention to detail. You will not be able to correct mistakes on the fly or suddenly pivot when kids are disengaged.</p>
<h2>4. Individual Touchpoints Are Game-Changers</h2>
<p>You can create these touchpoints through any medium you like: emails, video messages, phone calls, messages through your learning management system, comments on shared documents, etc.</p>
###
[Title]: 3 Best Free Image Converter Software Programs
[Blog article]: <h1>3 Best Free Image Converter Software Programs</h1>
<p>Best free image converters for JPG, BMP, PSD, TIF, GIF, RAW, and more</p>
<h2>1. XnConvert</h2>
<p>XnConvert is the Swiss Army knife of image converters. With XnView, you can convert any of around 500 image formats to your choice of around 80 others. If you have a rare image format that you can't open, XnView can probably convert it.</p>
<h2>2. CoolUtils Online Image Converter</h2>
<p>The CoolUtils Online Image Converter is just that—an image converter that exists completely online, no download required. Unlike some online image converters, this one does the image converting for you in real-time—no waiting on an email link.</p>
<h2>3. FileZigZag</h2>
<p>FileZigZag is another online image converter service that will convert most common graphics formats. Just upload the original image, choose the desired output, and then wait for the download link to appear on the page.</p>
###
[Title]: 4 Best Tips to Find a Girlfriend
[Blog article]: """,
max_length=500,
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Produksjon:
<h1>Text Generation API</h1>
<h2>What is Text Generation?</h2>
<p>Text generation is the process of generating text from a block of text. It is not simply the inverse of summarization: a text generator will take a short piece of text as an input and generate a longer one.</p>
<p>For example you have the following text:</p>
Ahead of the opening of the meeting,
<p>In this case the goal of the API is to automatically generate the following:</p>
Ahead of the opening of the meeting, Prime Minister Justin Trudeau spoke to reporters at the Montreal airport where he was travelling to speak at the conference.
<p>So basically we want to leverage the output of the API as the input for the text generator, and we will then be able to generate some sentences based on the input we already have.</p>
<h2>Text generation with GPT-2</h2>
<p>We will leverage GPT-2 in order to have a starting point for the text generator. In this case, we will use the API as the input for the text generator, and we will use the output of the API as the input for GPT-2.
However, we want to fine-tune GPT-2 to generate more complex sentences and to have better results.</p>
Er det ikke imponerende? Denne genererte bloggartikkelen er liten, men du kan generere mye lengre artikler. Strukturen strukturen til det genererte blogginnlegget avhenger egentlig av strukturen du brukte i eksemplene med få bilder. For å få mer komplekse strukturer og mer relevant innhold, er finjustering av GPT-J nøkkelen.
Som du kan se, er læring med få skudd en flott teknikk som hjelper GPT-3, GPT-J og GPT-NeoX med å oppnå fantastiske ting! Nøkkelen her er å sende en korrekt kontekst før du gjør forespørselen din.
Selv for enkel tekstgenerering anbefales det å overføre så mye kontekst som mulig, for å hjelpe modellen.
Håper du fant det nyttig! Hvis du har noen spørsmål om hvordan du kan få mest mulig ut av disse modellene, vennligst ikke nøl med å spørre oss.
François
Fullstack-ingeniør hos NLP Cloud