Mixtral-8x7B è ora disponibile in Amazon SageMaker JumpStart | Servizi Web di 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)

Ottieni il seguente output:

> 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)

I modelli Mixtral possono fornire la comprensione come mostrato nel seguente output con la logica matematica:

> 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.

ripulire

Dopo aver terminato l'esecuzione del notebook, elimina tutte le risorse create nel processo in modo che la fatturazione venga interrotta. Utilizza il seguente codice:

predictor.delete_model()
predictor.delete_endpoint()

In questo post ti abbiamo mostrato come iniziare con Mixtral-8x7B in SageMaker Studio e distribuire il modello per l'inferenza. Poiché i modelli di base sono pre-addestrati, possono contribuire a ridurre i costi di formazione e infrastruttura e consentire la personalizzazione per il tuo caso d'uso. Visita subito SageMaker JumpStart in SageMaker Studio per iniziare.

Risorse

Circa gli autori

Rachna Chada è Principal Solution Architect AI/ML in Strategic Accounts presso AWS. Rachna è un'ottimista che crede che l'uso etico e responsabile dell'IA possa migliorare la società in futuro e portare prosperità economica e sociale. Nel tempo libero, a Rachna piace passare il tempo con la sua famiglia, fare escursioni e ascoltare musica.

Dottor Kyle Ulrich è uno scienziato applicato con il Algoritmi integrati di Amazon SageMaker squadra. I suoi interessi di ricerca includono algoritmi di machine learning scalabili, visione artificiale, serie storiche, bayesiani non parametrici e processi gaussiani. Il suo dottorato di ricerca è presso la Duke University e ha pubblicato articoli su NeurIPS, Cell e Neuron.

Christopher Whitten è uno sviluppatore di software nel team JumpStart. Aiuta a ridimensionare la selezione dei modelli e a integrare i modelli con altri servizi SageMaker. Chris è appassionato di accelerare l'ubiquità dell'intelligenza artificiale in una varietà di settori aziendali.

Dott. Fabio Nonato de Paula è un Senior Manager, Specialist GenAI SA, che aiuta i fornitori di modelli e i clienti a scalare l'intelligenza artificiale generativa in AWS. Fabio ha una passione per la democratizzazione dell'accesso alla tecnologia dell'intelligenza artificiale generativa. Fuori dal lavoro, puoi trovare Fabio in sella alla sua moto sulle colline della Sonoma Valley o leggendo Comixology.

Dottor Ashish Khetan è un Senior Applied Scientist con algoritmi integrati di Amazon SageMaker e aiuta a sviluppare algoritmi di machine learning. Ha conseguito il dottorato di ricerca presso l'Università dell'Illinois Urbana-Champaign. È un ricercatore attivo nell'apprendimento automatico e nell'inferenza statistica e ha pubblicato numerosi articoli nelle conferenze NeurIPS, ICML, ICLR, JMLR, ACL e EMNLP.

Carlo Albertsen guida prodotti, ingegneria e scienza per Amazon SageMaker Algorithms e JumpStart, l'hub di machine learning di SageMaker. È appassionato di applicare l'apprendimento automatico per sbloccare il valore aziendale.