Mixtral-8x7B est désormais disponible dans Amazon SageMaker JumpStart | Services Web Amazon

from sagemaker.jumpstart.model import JumpStartModel model = JumpStartModel(model_id="huggingface-llm-mixtral-8x7b")
predictor = model.deploy()

payload = {"inputs": "Hello!"} predictor.predict(payload)

# Code generation
payload = { "inputs": "Write a program to compute factorial in python:", "parameters": { "max_new_tokens": 200, },
}
predictor.predict(payload)

Input Text: Write a program to compute factorial in python:
Generated Text:
Factorial of a number is the product of all the integers from 1 to that number. For example, factorial of 5 is 1*2*3*4*5 = 120. Factorial of 0 is 1. Factorial of a negative number is not defined. The factorial of a number can be written as n!. For example, 5! = 120. ## Write a program to compute factorial in python ```
def factorial(n):
if n == 0:
return 1
else:
return n * factorial(n-1) print(factorial(5))
``` Output: ```
120
``` ## Explanation: In the above program, we have defined a function called factorial which takes a single argument n. If n is equal to 0, then we return 1. Otherwise, we return n multiplied by the factorial of n-1. We then call the factorial function with the argument 5 and print the result. The output of the program is 120, which is the factorial of 5. ## How to compute factorial in python In the above program, we have used a recursive function to compute the factorial of a number. A recursive function is a function that calls itself. In this case, the factorial function calls itself with the argument n-1. This process continues until n is equal to 0, at which point the function returns 1. The factorial of a number can also be computed using a loop. For example, the following program uses a for loop to compute the factorial of a number: ```
def factorial(n):
result = 1
for i in range(1, n+1):
result *= i
return result

payload = { "inputs": """
Tweet: "I hate it when my phone battery dies."
Sentiment: Negative Tweet: "My day has been :+1:"
Sentiment: Positive Tweet: "This is the link to the article"
Sentiment: Neutral Tweet: "This new music video was incredibile"
Sentiment:""", "parameters": { "max_new_tokens": 2,
},
}
predictor.predict(payload)

Input Text: Tweet: "I hate it when my phone battery dies."
Sentiment: Negative
###
Tweet: "My day has been :+1:"
Sentiment: Positive
###
Tweet: "This is the link to the article"
Sentiment: Neutral
###
Tweet: "This new music video was incredibile"
Sentiment:
Generated Text:  Positive

# Question answering
payload = { "inputs": "Could you remind me when was the C programming language invented?", "parameters": { "max_new_tokens": 100, },
}
query_endpoint(payload)

Input Text: Could you remind me when was the C programming language invented?
Generated Text: C was invented in 1972 by Dennis Ritchie at Bell Labs. C is a general-purpose programming language. It was invented to write the UNIX operating system. C is a structured programming language. It is a middle-level language. It is a procedural language. C is a compiled language. It is a portable language. C is a case-sensitive language. It is a free-form language

<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]]

instructions = [{"role": "user", "content": "what is the recipe of mayonnaise?"}]
prompt = format_instructions(instructions)
payload = { "inputs": prompt, "parameters": {"max_new_tokens": 315, "do_sample": True}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

> Input
<s>[INST] what is the recipe of mayonnaise? [/INST]</s> > Output
Here is a simple recipe for homemade mayonnaise: Ingredients: * 1 egg yolk
* 1 tablespoon of mustard (Dijon is a good choice)
* 1 cup of oil (canola or vegetable oil work well)
* 1-2 tablespoons of white vinegar or lemon juice
* Salt to taste Instructions: 1. In a medium bowl, whisk together the egg yolk and mustard. It is important that these ingredients are at room temperature.
2. Start adding the oil drop by drop, whisking continuously. This step is crucial to ensure that the mayonnaise emulsifies and does not separate.
3. Once you have added about a quarter of the oil and the mixture has thickened, you can start adding the oil in a thin stream, still whisking constantly.
4. When all the oil has been incorporated and the mayonnaise is thick, whisk in the vinegar or lemon juice and salt to taste.
5. If the mayonnaise is too thick, you can thin it with a little water.
6. Store the mayonnaise in the refrigerator and use within a few days. Note: It is important to use pasteurized eggs or egg yolks when making homemade mayonnaise to reduce the risk of foodborne illness.

instructions = [
{ "role": "user", "content": "In Bash, how do I list all text files in the current directory (excluding subdirectories) that have been modified in the last month?",
}
]
prompt = format_instructions(instructions)
payload = { "inputs": prompt, "parameters": {"max_new_tokens": 256, "do_sample": True, "temperature": 0.2}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

Vous obtenez la sortie suivante:

> Input
<s>[INST] In Bash, how do I list all text files in the current directory (excluding subdirectories) that have been modified in the last month? [/INST]</s>
> Output
ef{0.15cm} To list all text files in the current directory that have been modified in the last month, you can use a combination of the `find` and `grep` commands in Bash. Here's the command you're looking for: ```bash
find . -maxdepth 1 -type f -name "*.txt" -mtime -30
``` Let's break down this command: - `find .` starts a search in the current directory.
- `-maxdepth 1` limits the search to the current directory only (excluding subdirectories).
- `-type f` specifies that you're looking for files.
- `-name "*.txt"` filters the results to only include files with a `.txt` extension.
- `-mtime -30` filters the results to only include files modified within the last 30 days. This command will output the paths of all text files in the current directory that have been modified in the last month.

instructions = [
{ "role": "user", "content": "I bought an ice cream for 6 kids. Each cone was $1.25 and I paid with a $10 bill. How many dollars did I get back? Explain first before answering.",
}
]
prompt = format_instructions(instructions)
payload = { "inputs": prompt, "parameters": {"max_new_tokens": 600, "do_sample": True, "temperature": 0.2}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

Les modèles mixtral peuvent fournir une compréhension comme le montre le résultat suivant avec la logique mathématique :

> Input
<s>[INST] I bought an ice cream for 6 kids. Each cone was $1.25 and I paid with a $10 bill. How many dollars did I get back? Explain first before answering. [/INST] </s>
> Output
First, let's calculate the total cost of the ice cream cones. Since each cone costs $1.25 and you bought 6 cones, the total cost would be: Total cost = Cost per cone * Number of cones
Total cost = $1.25 * 6
Total cost = $7.50 Next, subtract the total cost from the amount you paid with the $10 bill to find out how much change you got back: Change = Amount paid - Total cost
Change = $10 - $7.50
Change = $2.50 So, you got $2.50 back.

Nettoyer

Une fois que vous avez terminé d'exécuter le bloc-notes, supprimez toutes les ressources que vous avez créées au cours du processus afin que votre facturation soit arrêtée. Utilisez le code suivant :

predictor.delete_model()
predictor.delete_endpoint()

Dans cet article, nous vous avons montré comment démarrer avec Mixtral-8x7B dans SageMaker Studio et déployer le modèle pour l'inférence. Étant donné que les modèles de base sont pré-entraînés, ils peuvent contribuer à réduire les coûts de formation et d’infrastructure et permettre une personnalisation adaptée à votre cas d’utilisation. Visitez SageMaker JumpStart dans SageMaker Studio dès maintenant pour commencer.

Resources

À propos des auteurs

Rachna Chadha est architecte principal de solutions AI/ML dans les comptes stratégiques chez AWS. Rachna est une optimiste qui croit qu'une utilisation éthique et responsable de l'IA peut améliorer la société à l'avenir et apporter la prospérité économique et sociale. Dans ses temps libres, Rachna aime passer du temps avec sa famille, faire de la randonnée et écouter de la musique.

Dr Kyle Ulrich est un scientifique appliqué avec le Algorithmes intégrés d'Amazon SageMaker équipe. Ses intérêts de recherche comprennent les algorithmes d'apprentissage automatique évolutifs, la vision par ordinateur, les séries chronologiques, les processus bayésiens non paramétriques et gaussiens. Son doctorat est de l'Université Duke et il a publié des articles dans NeurIPS, Cell et Neuron.

Christophe Whitten est un développeur de logiciels au sein de l'équipe JumpStart. Il aide à mettre à l'échelle la sélection de modèles et à intégrer des modèles avec d'autres services SageMaker. Chris est passionné par l'accélération de l'omniprésence de l'IA dans une variété de domaines commerciaux.

Dr Fabio Nonato de Paula est un directeur principal chez Specialist GenAI SA, qui aide les fournisseurs de modèles et les clients à faire évoluer l'IA générative dans AWS. Fabio a une passion pour démocratiser l’accès à la technologie d’IA générative. En dehors du travail, vous pouvez trouver Fabio conduisant sa moto dans les collines de la vallée de Sonoma ou lisant ComiXology.

Dr Ashish Khetan est un scientifique appliqué senior avec les algorithmes intégrés d'Amazon SageMaker et aide à développer des algorithmes d'apprentissage automatique. Il a obtenu son doctorat à l'Université de l'Illinois à Urbana-Champaign. Il est un chercheur actif en apprentissage automatique et en inférence statistique, et a publié de nombreux articles dans les conférences NeurIPS, ICML, ICLR, JMLR, ACL et EMNLP.

Karl Albertsen dirige les produits, l'ingénierie et la science pour les algorithmes Amazon SageMaker et JumpStart, le centre d'apprentissage automatique de SageMaker. Il est passionné par l'application de l'apprentissage automatique pour libérer de la valeur commerciale.