GPT-3, GPT-J și GPT-Neo sunt modele de inteligență artificială foarte puternice. Vă arătăm aici cum să folosiți eficient aceste modele datorită învățării în câteva lovituri. Few-shot learning este ca și cum ați antrena/rafina un model de inteligență artificială, dând pur și simplu câteva exemple în prompt.
GPT-3, lansat de OpenAI, este cel mai puternic model de inteligență artificială lansat vreodată pentru înțelegerea și generarea de texte.
A fost antrenată pe 175 de miliarde de parametri, ceea ce o face extrem de versatilă și capabilă să înțeleagă aproape orice!
Puteți face tot felul de lucruri cu GPT-3, cum ar fi chatbots, crearea de conținut, extragerea de entități, clasificarea, rezumarea și multe altele. Dar este nevoie de ceva practică și utilizarea corectă a acestui model nu este ușoară.
GPT-Neo și GPT-J sunt ambele modele de procesare a limbajului natural open-source, create de un colectiv de cercetători care lucrează pentru a deschide sursa AI (vezi site-ul EleutherAI).
GPT-J are 6 miliarde de parametri, ceea ce îl face cel mai avansat sistem open-source de procesare a limbajului natural. deschis la momentul redactării acestui document. Acesta este o alternativă directă la GPT-3 Curie, un model proprietar al OpenAI.
Aceste modele sunt foarte versatile. Ele pot fi utilizate pentru aproape orice caz de utilizare a procesării limbajului natural: generare de text, sentiment analiză de text, clasificare, traducere automată,... și multe altele (a se vedea mai jos). Cu toate acestea, utilizarea lor eficientă necesită uneori practică. De asemenea, timpul de răspuns (latența) poate fi mai mare decât în cazul procesării limbajului natural mai standard. mai obișnuite.
GPT-J și GPT-Neo sunt ambele disponibile pe NLP Cloud API. Mai jos, vă prezentăm exemple obținute
utilizând
GPT-J endpoint al NLP Cloud pe GPU, cu clientul Python. Dacă doriți să copiați exemplele cu copy paste,
vă rugăm să accesați
nu uitați să adăugați propriul token API. Pentru a instala clientul Python, rulați mai întâi următoarele: pip install nlpcloud.
Învățarea cu câteva lovituri constă în a ajuta un model de învățare automată să facă predicții datorită doar câtorva exemple. Nu este nevoie să antrenați un nou model aici: modele precum GPT-3, GPT-J și GPT-Neo sunt atât de mari încât pot să se adapteze cu ușurință la multe contexte fără a fi reantrenate.
Oferirea doar a câtorva exemple modelului îl ajută pe acesta să își sporească dramatic acuratețea.
În procesarea limbajului natural, ideea este de a transmite aceste exemple împreună cu textul introdus. Vedeți exemplele de mai jos!
De asemenea, rețineți că, dacă învățarea în câteva lovituri nu este suficientă, puteți, de asemenea, să reglați fin GPT-3 pe site-ul OpenAI și GPT-J pe NLP Cloud, astfel încât modelul este perfect adaptat la cazul dvs. de utilizare.
Puteți testa cu ușurință învățarea în câteva lovituri pe terenul de joacă NLP Cloud (încercați-o aici).
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"])Ieșire:
PositiveDupă cum puteți vedea, faptul că mai întâi dăm 3 exemple cu un format adecvat, îl determină pe GPT-J să înțeleagă că dorim să efectuăm o analiză a sentimentelor. Iar rezultatul său este bun.
Puteți ajuta GPT-J să înțeleagă diferitele
secțiuni utilizând un delimitator personalizat, cum ar fi următorul: ###. Ne-ar prinde foarte bine și altceva de genul acesta: ---. Sau pur și simplu un nou
linie. Apoi se stabilește "end_sequence", care este un parametru NLP Cloud care
îi spune lui GPT-J să oprească generarea de conținut după o nouă linie + ###: 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"])Ieșire:
<h1 style=color: white;>Welcome to AI</h1>Generarea de cod cu GPT-J este cu adevărat uimitoare. Acest lucru se datorează parțial faptului că GPT-J a fost antrenat pe un număr mare de baze de coduri uriașe.
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"])
Ieșire:
SELECT * FROM Employee ORDER BY ID DESC LIMIT 3;Generarea automată a SQL funcționează foarte bine cu GPT-J, în special datorită naturii declarative a SQL, iar faptului că SQL este un limbaj destul de limitat, cu relativ puține posibilități (în comparație cu majoritatea limbajele de programare).
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.
""",
length_no_input=True,
end_sequence="###",
remove_end_sequence=True,
remove_input=True)
print(generation["generated_text"])
Ieșire:
[Name]: David Melvin
[Position]: Senior Adviser
[Company]: CITIC CLSA
După cum puteți vedea, GPT-J se pricepe foarte bine la extragerea datelor structurate din text nestructurat. Este cu adevărat impresionant modul în care GPT-J rezolvă extragerea entităților fără a fi nevoie de reeducare! De obicei, extragerea de noi tipuri de entități (cum ar fi numele, poziția, țara etc.) necesită un întreg proces nou de adnotare, instruire, implementare... În acest caz, este complet transparent.
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"])
Ieșire:
Planul GPURăspunsul la întrebări funcționează foarte bine. Acesta poate fi realizat și cu alte modele dedicate de procesare a limbajului natural, dar poate că nu cu aceeași nivel de acuratețe.
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"])
Ieșire:
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.După cum puteți vedea, este destul de impresionant modul în care GPT-J urmărește automat formatarea inițială, iar conținutul generat este, de asemenea, foarte bun. Ați putea crea un tort propriu-zis din asta (nu am încercat încă totuși).
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"])
Ieșire:
Nu vreau să plec.Corecțiile ortografice și gramaticale funcționează conform așteptărilor. Dacă doriți să fiți mai precis cu privire la locația greșeala în propoziție, ar fi bine să folosiți totuși un model dedicat.
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"])
Ieșire:
NLP Cloud makes it easy to deploy NLP to production.Traducerea automată necesită, de obicei, modele dedicate (adesea 1 pentru fiecare limbă). În acest caz, toate limbile sunt tratate din start de GPT-J, ceea ce este destul de impresionant.
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"])
Ieșire:
People want a way to get the benefits of NLP without paying for it.Iată un mod amuzant și ușor de a genera tweet-uri scurte în funcție de un context.
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"])
Ieșire:
Oh? How did that happen?După cum puteți vedea, GPT-J înțelege în mod corespunzător că vă aflați într-un mod conversațional. Iar funcția foarte puternică foarte puternic este că, dacă schimbați tonul în context, răspunsurile din partea modelului vor fi la fel. ton (sarcasm, furie, curiozitate...).
De fapt, am scris un articol de blog dedicat despre cum să construim un chatbot cu GPT-3/GPT-J, nu ezitați să o citiți!
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"])
Ieșire:
learn chineseEste destul de impresionant modul în care GPT-J poate detecta intenția din fraza dumneavoastră. Funcționează foarte bine pentru mai multe mai complexe. Puteți chiar să îi cereți să să formateze intenția în mod diferit, dacă doriți. De exemplu, ați putea genera automat un fișier Javascript de tipul "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"])
Ieșire:
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 a făcut modificări la paragraful nostru, păstrând însă sensul principal, care este ceea ce este parafrazarea. Ați putea încuraja perfect GPT-J să redea mai multe parafraze originale, prin trecând diferite exemple la intrare și jucându-vă cu parametrii API, cum ar fi temperatura, top_p, penalizarea repetiției...
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"])
Ieșire:
Season 3 of Succession ended with Logan Roy trying to sell his company to Lukas Matsson.Rezumatul textului este o sarcină dificilă. GPT-J se descurcă foarte bine în acest sens, atâta timp cât îi oferiți exemple. Dimensiunea rezumatului și tonul acestuia depind foarte mult de exemplele pe care le dați. create. De exemplu, s-ar putea să nu creați același tip de exemple, fie că încercați să faceți o rezumat simplu pentru copii sau un rezumat medical avansat pentru medici. Dacă dimensiunea de intrare a GPT-J este prea mică pentru exemplele dumneavoastră de rezumat, este posibil să doriți să ajustați GPT-J pentru sarcina dumneavoastră de rezumare.
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"])
Ieșire:
foodIată un mod simplu și puternic de a clasifica un text datorită așa-numitei "fotografii zero". învățare", fără a fi nevoie să declarați în prealabil categoriile.
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"])
Ieșire:
paragraphs, transformer, input, errorsExtracția de cuvinte cheie constă în extragerea ideilor principale dintr-un text. Aceasta este o activitate interesantă de prelucrare a limbajului natural subdomeniu interesant pe care GPT-J îl poate gestiona foarte bine. A se vedea mai jos pentru extragerea frazelor-cheie (același lucru, dar cu mai multe cuvinte).
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"])
Ieșire:
large documents, paragraph, mean poolingAcelași exemplu ca mai sus, doar că de data aceasta nu dorim să extragem un singur cuvânt, ci mai multe cuvinte (numite fraze-cheie).
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"])
Ieșire:
Extraordinary t-shirt for men, for $39 only.Este posibil să solicitați GPT-J să genereze o descriere de produs sau un anunț care să conțină anumite cuvinte cheie. Aici suntem doar generăm o propoziție simplă, dar am putea genera cu ușurință un paragraf întreg dacă este necesar.
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"])
Ieșire:
<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>Nu-i așa că este impresionant? Acest articol de blog generat este mic, dar puteți genera articole mult mai lungi. Site-ul structură a articolului de blog generat depinde într-adevăr de structura pe care ați folosit-o în exemplele de câteva fotografii. Pentru a obține structuri mai complexe și un conținut mai relevant, reglarea fină a GPT-J este cheia.
După cum puteți vedea, învățarea în câteva lovituri este o tehnică excelentă care ajută GPT-3, GPT-J și GPT-Neo să obțină rezultate uimitoare. lucruri uimitoare! Cheia aici este să treceți un context corect înainte de a face solicitarea.
Chiar și pentru generarea unui text simplu, este recomandat să se treacă cât mai mult context posibil, pentru a ajuta la modelul.
Sper că v-a fost de folos! Dacă aveți întrebări despre cum să profitați la maximum de aceste modele, vă rugăm să nu ezitați să ne întrebați.
Julien Salinas
CTO la NLP Cloud