GPT-3, GPT-J et GPT-Neo sont des modèles d'IA très puissants. Nous vous montrons ici comment utiliser efficacement ces modèles grâce au few-shot learning. L'apprentissage en quelques clics revient à entraîner/affiner un modèle d'IA, en donnant simplement quelques exemples dans votre message.
GPT-3, publié par OpenAI, est le modèle d'IA le plus puissant jamais publié pour la compréhension et la génération de textes.
Il a été entraîné sur 175 milliards de paramètres, ce qui le rend extrêmement polyvalent et capable de comprendre à peu près tout !
Vous pouvez faire toutes sortes de choses avec GPT-3 comme des chatbots, la création de contenu, l'extraction d'entités, la classification, le résumé et bien plus encore. Mais cela demande un peu de pratique et utiliser ce modèle correctement n'est pas facile.
GPT-Neo et GPT-J sont tous deux des modèles de traitement du langage naturel à code source ouvert, créés par un collectif de chercheurs qui travaillent à l'élaboration d'une IA à code source ouvert. chercheurs travaillant à l'open source de l'IA (voir le site web d'EleutherAI).
GPT-J possède 6 milliards de paramètres, ce qui en fait le modèle de traitement du langage naturel open-source le plus avancé à ce jour. open-source le plus avancé à ce jour. Il s'agit d'une alternative directe au modèle propriétaire GPT-3 Curie d'OpenAI.
Ces modèles sont très polyvalents. Ils peuvent être utilisés pour presque tous les cas d'utilisation du traitement du langage naturel : génération de textes, analyse de sentiments, etc. analyse de sentiments, classification, traduction automatique,... et bien plus encore (voir ci-dessous). Cependant, leur utilisation efficace nécessite parfois de la pratique. Leur temps de réponse (latence) peut également être plus long que les modèles de traitement du langage naturel plus standard. plus standards.
GPT-J et GPT-Neo sont tous deux disponibles sur l'API NLP Cloud. Ci-dessous, nous vous montrons des exemples obtenus
en utilisant le
GPT-J de NLP Cloud sur GPU, avec le client Python. Si vous voulez copier-coller les exemples,
veuillez consulter
n'oubliez pas d'ajouter votre propre jeton API. Afin d'installer le client Python, exécutez d'abord ce qui suit : pip install nlpcloud.
Le Few-shot Learning consiste à aider un modèle d'apprentissage automatique à faire des prédictions à partir de quelques exemples seulement. exemples. Il n'est pas nécessaire d'entraîner un nouveau modèle : les modèles tels que GPT-3, GPT-J et GPT-Neo sont si grands qu'ils peuvent facilement s'adapter à de nombreux contextes sans être entraînés à nouveau. s'adapter facilement à de nombreux contextes sans être réentraînés.
Le fait de ne donner que quelques exemples au modèle lui permet d'augmenter considérablement sa précision.
Dans le traitement du langage naturel, l'idée est de transmettre ces exemples avec votre entrée de texte. Voir les exemples ci-dessous !
Notez également que, si l'apprentissage en quelques coups n'est pas suffisant, vous pouvez également affiner GPT-3 sur le site d'OpenAI et GPT-J sur NLP Cloud afin que le modèle soit parfaitement adapté à votre cas d'utilisation.
Vous pouvez facilement tester l'apprentissage "few-shot" sur le terrain de jeu NLP Cloud. (Essayez-le ici).
Test sur le cour de récréation
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"])Sortie:
PositiveComme vous pouvez le voir, le fait que nous donnions d'abord 3 exemples avec un format approprié, amène GPT-J à comprendre que nous voulons faire une analyse des sentiments. Et son résultat est bon.
Vous pouvez aider GPT-J à comprendre les différentes
sections en utilisant un délimiteur personnalisé comme le suivant : ###. Nous pourrions parfaitement utiliser quelque chose d'autre comme ça : ---. Ou simplement une nouvelle
ligne. Ensuite, nous définissons "end_sequence" qui est un paramètre du NLP Cloud qui
indique à GPT-J d'arrêter de générer du contenu après une nouvelle ligne. + ###: 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"])Sortie:
<h1 style=color: white;>Welcome to AI</h1>La génération de code avec GPT-J est vraiment étonnante. C'est en partie grâce au fait que GPT-J a été entraîné sur d'énormes bases de code.
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"])
Sortie:
SELECT * FROM Employee ORDER BY ID DESC LIMIT 3;La génération automatique de SQL fonctionne très bien avec GPT-J, surtout en raison de la nature déclarative de SQL, et le fait que SQL soit un langage assez limité avec relativement peu de possibilités (comparé à la plupart des langages de programmation).
Test sur le cour de récréation
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"])
Sortie:
[Name]: David Melvin
[Position]: Senior Adviser
[Company]: CITIC CLSA
Comme vous pouvez le constater, GPT-J est très efficace pour extraire des données structurées d'un texte non structuré. C'est vraiment impressionnant de voir comment GPT-J résout l'extraction d'entités sans même avoir besoin d'une nouvelle formation ! En général, l'extraction de nouveaux types d'entités (comme le nom, la position, le pays, etc.) nécessite un tout nouveau processus d'annotation, de formation, de déploiement, etc. annotation, formation, déploiement... Ici, c'est complètement transparent.
Test sur le cour de récréation
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"])
Sortie:
Plan GPULa réponse aux questions fonctionne très bien. Elle peut également être réalisée avec d'autres modèles dédiés au traitement du langage naturel, mais peut-être pas avec le même niveau de précision.
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"])
Sortie:
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.Comme vous pouvez le voir, il est assez impressionnant de voir comment GPT-J suit automatiquement votre formatage initial, et le contenu généré est également très bon. contenu généré est également très bon. Vous pourriez en faire un vrai gâteau (je n'ai pas encore essayé). cependant).
Test sur la cour de récréation
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"])
Sortie:
Je ne veux pas y aller.Les corrections orthographiques et grammaticales fonctionnent comme prévu. Si vous souhaitez être plus précis quant à l'emplacement de la l'erreur dans la phrase, vous pouvez utiliser un modèle dédié.
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"])
Sortie:
NLP Cloud makes it easy to deploy NLP to production.La traduction automatique fait généralement appel à des modèles dédiés (souvent un par langue). Ici, toutes les langues sont traitées par GPT-J, ce qui est assez impressionnant.
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"])
Sortie:
People want a way to get the benefits of NLP without paying for it.Voici un moyen simple et amusant de générer de courts tweets suivant un contexte.
Test sur la cour de récréation
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"])
Sortie:
Oh? How did that happen?Comme vous pouvez le constater, GPT-J comprend correctement que vous êtes en mode conversationnel. Et ce qui est très puissant est que, si vous changez le ton dans votre contexte, les réponses du modèle suivront le même ton (sarcasme, colère, curiosité...). ton (sarcasme, colère, curiosité...).
Nous avons en fait écrit un article de blog dédié sur la façon de construire un chatbot avec GPT-3/GPT-J, N'hésitez pas à le lire !
Test sur le cour de récréation
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"])
Sortie:
learn chineseC'est assez impressionnant de voir comment GPT-J peut détecter l'intention à partir de votre phrase. Il fonctionne très bien pour les phrases plus complexes. Vous pouvez même lui demander de de formater l'intention différemment si vous le souhaitez. Par exemple, vous pouvez générer automatiquement un nom de fonction Javascript comme "learnChinese".
Test sur le cour de récréation
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"])
Sortie:
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 apporté des modifications à notre paragraphe, tout en gardant le sens principal, ce qui est le but de la de la paraphrase. Vous pourriez parfaitement encourager GPT-J à retourner des paraphrases plus originales, en passant différents exemples en entrée, et en jouant avec les paramètres de l'API comme la température, top_p, la pénalité de répétition...
Test sur le cour de récréation
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"])
Sortie:
Season 3 of Succession ended with Logan Roy trying to sell his company to Lukas Matsson.Le résumé de texte est une tâche délicate. GPT-J est très bon pour cela, tant que vous lui donnez les bons exemples. exemples. La taille du résumé, et le ton du résumé, dépendent beaucoup des exemples que vous avez créés. créés. Par exemple, vous ne créerez peut-être pas le même type d'exemples si vous essayez de faire un résumé simple pour les enfants ou un résumé avancé. résumé simple pour les enfants, ou un résumé médical avancé pour les médecins. Si la taille d'entrée de GPT-J est trop petite pour vos exemples de résumé, vous pouvez affiner GPT-J pour votre tâche de résumé.
Test sur le cour de récréation
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"])
Sortie:
foodVoici un moyen simple et puissant de catégoriser un texte grâce à la technique dite de "l'apprentissage à zéro coup", sans avoir à déclarer les catégories à l'avance. sans avoir à déclarer des catégories à l'avance.
Testez sur la cour de récréation
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"])
Sortie:
paragraphs, transformer, input, errorsL'extraction de mots-clés consiste à extraire les idées principales d'un texte. Il s'agit d'un sous-domaine intéressant du traitement du langage naturel que GPT-J peut très bien gérer. Voir ci-dessous pour l'extraction de phrases-clés (même chose mais avec plusieurs mots). plusieurs mots).
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"])
Sortie:
large documents, paragraph, mean poolingMême exemple que ci-dessus sauf que cette fois-ci nous ne voulons pas extraire un seul mot mais plusieurs mots (appelé keyphrase).
Testez sur la cour de récréation
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"])
Sortie:
Extraordinary t-shirt for men, for $39 only.Il est possible de demander à GPT-J de générer une description de produit ou une annonce contenant des mots-clés spécifiques. Ici nous ne faisons que une simple phrase, mais nous pourrions facilement générer un paragraphe entier si nécessaire.
Test sur le cour de récréation
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"])
Sortie:
<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>N'est-ce pas impressionnant ? Cet article de blog généré est petit mais vous pouvez générer des articles beaucoup plus longs. La structure structure de l'article de blog généré dépend réellement de la structure que vous avez utilisée dans vos quelques exemples. Afin d'obtenir des structures plus complexes et un contenu plus pertinent, le réglage fin de GPT-J est la clé.
Comme vous pouvez le constater, l'apprentissage en quelques coups est une excellente technique qui permet aux GPT-3, GPT-J et GPT-Neo de réaliser des choses étonnantes. choses ! La clé ici est de passer un contexte correct avant de faire votre demande.
Même pour une simple génération de texte, il est recommandé de transmettre le plus de contexte possible, afin d'aider le modèle. le modèle.
J'espère que vous l'avez trouvé utile ! Si vous avez des questions sur la façon de tirer le meilleur parti de ces modèles, n'hésitez pas à nous les poser. n'hésitez pas à nous les poser.
Julien Salinas
Directeur technique de NLP Cloud