GPT-3, GPT-J und GPT-Neo sind sehr leistungsfähige KI-Modelle. Wir zeigen Ihnen hier, wie Sie diese Modelle dank des "few-shot learning" effektiv nutzen können. Few-Shot-Lernen ist wie das Trainieren/Feinabstimmen eines KI-Modells, indem Sie einfach ein paar Beispiele in Ihrem Prompt eingeben.
Das von OpenAI herausgegebene GPT-3 ist das leistungsfähigste KI-Modell, das jemals für Textverständnis und Texterstellung veröffentlicht wurde.
Es wurde auf 175 Milliarden Parameter trainiert, was es extrem vielseitig macht und in der Lage, so ziemlich alles zu verstehen!
Mit GPT-3 kann man alles Mögliche machen, wie Chatbots, Inhaltserstellung, Entity-Extraktion, Klassifizierung, Zusammenfassung und vieles mehr. Es erfordert jedoch etwas Übung und die korrekte Verwendung dieses Modells ist nicht einfach.
GPT-Neo und GPT-J sind beides Open-Source-Modelle für die Verarbeitung natürlicher Sprache, die von einem Kollektiv von Forschern entwickelt wurden, die an der Forschern, die an Open Source AI arbeiten (siehe die Website von EleutherAI).
GPT-J hat 6 Milliarden Parameter und ist damit das fortschrittlichste Open-Source-Modell für natürliche Sprachverarbeitung Modell zum Zeitpunkt dieses Schreibens. Es ist eine direkte Alternative zu OpenAIs proprietärem GPT-3 Curie.
Diese Modelle sind sehr vielseitig. Sie können für fast jeden Anwendungsfall der natürlichen Sprachverarbeitung verwendet werden: Texterstellung, Sentiment Analyse, Klassifizierung, maschinelle Übersetzung, ... und vieles mehr (siehe unten). Sie effektiv zu nutzen erfordert manchmal etwas Übung. Ihre Reaktionszeit (Latenz) kann auch länger sein als bei Standardmodellen der natürlichen Sprachverarbeitung Modelle.
GPT-J und GPT-Neo sind beide über die NLP Cloud API verfügbar. Im Folgenden zeigen wir Ihnen Beispiele, die
unter Verwendung des
GPT-J Endpunkt der NLP Cloud auf GPU, mit dem Python-Client. Wenn Sie die Beispiele kopieren und einfügen möchten,
bitte
vergessen Sie nicht, Ihr eigenes API-Token hinzuzufügen. Um den Python-Client zu installieren, führen Sie zunächst Folgendes aus: pip install nlpcloud.
Beim Few-Shot-Learning geht es darum, einem maschinellen Lernmodell zu helfen, Vorhersagen zu treffen, die nur auf ein paar Beispiele. Hier ist es nicht nötig, ein neues Modell zu trainieren: Modelle wie GPT-3, GPT-J und GPT-Neo sind so groß, dass sie dass sie sich leicht an viele Kontexte anpassen können, ohne neu trainiert zu werden.
Wenn man dem Modell nur wenige Beispiele vorgibt, kann es seine Genauigkeit drastisch erhöhen.
Bei der Verarbeitung natürlicher Sprache besteht die Idee darin, diese Beispiele zusammen mit Ihrer Texteingabe zu übermitteln. Siehe die Beispiele unten!
Wenn Ihnen das Lernen mit wenigen Schüssen nicht ausreicht, können Sie auch GPT-3 auf der OpenAI-Website und GPT-J auf der NLP-Cloud feineinstellen, damit das Modell perfekt auf Ihren Anwendungsfall zugeschnitten ist.
Sie können auf der NLP-Cloud-Spielwiese ganz einfach das Lernen in wenigen Schritten testen (Versuchen Sie es hier).
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"])Ausgabe:
PositiveWie Sie sehen können, führt die Tatsache, dass wir zuerst 3 Beispiele mit einem geeigneten Format angeben, dazu, dass GPT-J versteht dass wir eine Stimmungsanalyse durchführen wollen. Und sein Ergebnis ist gut.
Sie können GPT-J helfen, die verschiedenen
Abschnitte zu verstehen, indem Sie ein benutzerdefiniertes Begrenzungszeichen wie das folgende verwenden: ###. So etwas könnten wir gut gebrauchen: ---. Oder einfach eine neue
Zeile. Dann setzen wir "end_sequence", einen NLP-Cloud-Parameter, der
GPT-J anweist, nach einer neuen Zeile keinen Inhalt mehr zu erzeugen + ###: 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"])Ausgabe:
<h1 style=color: white;>Welcome to AI</h1>Die Codegenerierung mit GPT-J ist wirklich erstaunlich. Dies ist zum Teil der Tatsache zu verdanken, dass GPT-J an riesigen Code-Basis trainiert wurde.
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"])
Ausgabe:
SELECT * FROM Employee ORDER BY ID DESC LIMIT 3;Die automatische SQL-Generierung funktioniert sehr gut mit GPT-J, insbesondere aufgrund der deklarativen Natur von SQL und der Tatsache, dass SQL eine recht begrenzte Sprache mit relativ wenigen Möglichkeiten ist (im Vergleich zu den meisten Programmiersprachen).
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"])
Ausgabe:
[Name]: David Melvin
[Position]: Senior Adviser
[Company]: CITIC CLSA
Wie Sie sehen können, ist GPT-J sehr gut darin, strukturierte Daten aus unstrukturiertem Text zu extrahieren. Es ist wirklich beeindruckend, wie GPT-J die Entitätsextraktion löst, ohne dass ein erneutes Training erforderlich ist! Normalerweise, die Extraktion neuer Arten von Entitäten (wie Name, Position, Land, etc.) einen ganz neuen Prozess der Annotation, Training, Einsatz... Hier ist es völlig nahtlos.
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"])
Ausgabe:
GPU-PlanDie Beantwortung von Fragen funktioniert sehr gut. Sie kann auch mit anderen speziellen Modellen der natürlichen Sprachverarbeitung erreicht werden, aber vielleicht nicht mit der gleichen der gleichen Genauigkeit.
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"])
Ausgabe:
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.Wie Sie sehen, ist es ziemlich beeindruckend, wie GPT-J automatisch Ihrer anfänglichen Formatierung folgt, und der generierte Inhalt ist ebenfalls sehr gut. Daraus könnte man eine richtige Torte machen (noch nicht ausprobiert allerdings).
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"])
Ausgabe:
Ich möchte nicht gehen.Rechtschreib- und Grammatikkorrekturen funktionieren wie erwartet. Wenn Sie genauer wissen wollen, wo der Fehler im Fehler im Satz zu finden, sollten Sie allerdings ein spezielles Modell verwenden.
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"])
Ausgabe:
NLP Cloud makes it easy to deploy NLP to production.Für die maschinelle Übersetzung werden in der Regel spezielle Modelle verwendet (oft 1 pro Sprache). Hier werden alle Sprachen von GPT-J verarbeitet, was ziemlich beeindruckend ist.
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"])
Ausgabe:
People want a way to get the benefits of NLP without paying for it.Hier ist eine witzige und einfache Möglichkeit, kurze Tweets zu erstellen, die einem Kontext folgen.
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"])
Ausgabe:
Oh? How did that happen?Wie Sie sehen können, erkennt GPT-J, dass Sie sich in einem Gesprächsmodus befinden. Und der Clou ist, dass, wenn Sie den Ton in Ihrem Kontext ändern, die Antworten des Modells demselben Ton folgen werden Tonfall (Sarkasmus, Wut, Neugier...).
Wir haben sogar einen eigenen Blog-Artikel darüber geschrieben, wie man einen Chatbot mit GPT-3/GPT-J, lesen Sie es ruhig!
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"])
Ausgabe:
learn chineseEs ist ziemlich beeindruckend, wie GPT-J die Absicht aus Ihrem Satz erkennen kann. Es funktioniert sehr gut bei komplexeren komplexen Sätzen. Sie können es sogar bitten die Absicht anders zu formatieren, wenn Sie wollen. Zum Beispiel könnten Sie automatisch einen Javascript Funktionsnamen wie "learnChinese" generieren.
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"])
Ausgabe:
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 hat Änderungen an unserem Absatz vorgenommen, dabei aber den wesentlichen Sinn beibehalten, denn darum geht es bei der Umschreibung geht. Sie könnten GPT-J durchaus dazu ermutigen, mehr originelle Umschreibungen zu liefern, indem Sie verschiedene Beispiele in der Eingabe übergeben und mit API-Parametern wie Temperatur, top_p, Wiederholungsstrafe...
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"])
Ausgabe:
Season 3 of Succession ended with Logan Roy trying to sell his company to Lukas Matsson.Das Zusammenfassen von Texten ist eine schwierige Aufgabe. GPT-J kann das sehr gut, wenn man ihm die richtigen Beispiele. Der Umfang der Zusammenfassung und der Ton der Zusammenfassung hängen sehr stark von den Beispielen ab, die Sie erstellt haben. Sie können zum Beispiel nicht dieselbe Art von Beispielen erstellen, egal ob Sie eine einfache Zusammenfassung für Kinder oder eine fortgeschrittene medizinische Zusammenfassung für Ärzte zu erstellen. Wenn die Eingabegröße von GPT-J für Ihre Zusammenfassungsbeispiele zu klein ist, sollten Sie GPT-J für Ihre Zusammenfassungsaufgabe feinabstimmen.
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"])
Ausgabe:
foodHier ist eine einfache und leistungsfähige Methode, um einen Text dank der sogenannten "Zero-Shot"-Technik zu kategorisieren Lernens", ohne dass die Kategorien im Voraus festgelegt werden müssen.
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"])
Ausgabe:
paragraphs, transformer, input, errorsBei der Extraktion von Schlüsselwörtern geht es darum, die wichtigsten Ideen aus einem Textstück herauszufiltern. Dies ist ein interessantes Teilgebiet der natürlichen Sprachverarbeitung Teilgebiet, das GPT-J sehr gut verarbeiten kann. Siehe unten für Keyphrase-Extraktion (dasselbe, aber mit mehreren Wörtern).
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"])
Ausgabe:
large documents, paragraph, mean poolingDasselbe Beispiel wie oben, nur dass wir dieses Mal nicht ein einzelnes Wort, sondern mehrere Wörter extrahieren wollen (Keyphrase genannt).
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"])
Ausgabe:
Extraordinary t-shirt for men, for $39 only.Es ist möglich, GPT-J zu bitten, eine Produktbeschreibung oder eine Anzeige mit bestimmten Schlüsselwörtern zu erstellen. Hier wir nur einen einfachen Satz, aber wir könnten bei Bedarf leicht einen ganzen Absatz generieren.
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"])
Ausgabe:
<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>Ist das nicht beeindruckend? Dieser generierte Blogartikel ist klein, aber Sie können viel längere Artikel erstellen. Die Struktur des generierten Blogbeitrags hängt wirklich von der Struktur ab, die Sie in Ihren Beispielen verwendet haben. Um komplexere Strukturen und relevantere Inhalte zu erhalten, ist die Feinabstimmung von GPT-J der Schlüssel.
Wie Sie sehen, ist das Lernen mit wenigen Schüssen eine großartige Technik, mit der GPT-3, GPT-J und GPT-Neo Erstaunliches erreichen Dinge zu erreichen! Der Schlüssel dazu ist, einen korrekten Kontext zu übergeben, bevor Sie Ihre Anfrage stellen.
Selbst bei der einfachen Texterstellung ist es empfehlenswert, so viel Kontext wie möglich zu übergeben, um das das Modell zu unterstützen.
Ich hoffe, Sie haben sie nützlich gefunden! Wenn Sie Fragen dazu haben, wie Sie das Beste aus diesen Modellen herausholen können, zögern Sie bitte nicht zögern Sie nicht, uns zu fragen.
Julien Salinas
CTO bei NLP Cloud