Mixtral-8x7B este acum disponibil în Amazon SageMaker JumpStart | Amazon Web Services

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)

Obțineți următoarea ieșire:

> 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)

Modelele Mixtral pot oferi înțelegere, așa cum se arată în următoarea ieșire, cu logica matematică:

> 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.

A curăța

După ce ați terminat de rulat blocnotesul, ștergeți toate resursele pe care le-ați creat în acest proces, astfel încât facturarea să fie oprită. Utilizați următorul cod:

predictor.delete_model()
predictor.delete_endpoint()

În această postare, v-am arătat cum să începeți cu Mixtral-8x7B în SageMaker Studio și să implementați modelul pentru inferență. Deoarece modelele de fundație sunt pregătite în prealabil, ele pot ajuta la reducerea costurilor de instruire și infrastructură și pot permite personalizarea pentru cazul dvs. de utilizare. Vizitați SageMaker JumpStart în SageMaker Studio acum pentru a începe.

Resurse

Despre autori

Rachna Chadha este arhitect principal de soluții AI/ML în conturi strategice la AWS. Rachna este o optimistă care crede că utilizarea etică și responsabilă a inteligenței artificiale poate îmbunătăți societatea în viitor și poate aduce prosperitate economică și socială. În timpul liber, Rachnei îi place să petreacă timpul cu familia ei, să facă drumeții și să asculte muzică.

Dr. Kyle Ulrich este un om de știință aplicat cu Algoritmi încorporați Amazon SageMaker echipă. Interesele sale de cercetare includ algoritmi scalabili de învățare automată, viziunea computerizată, serii temporale, non-parametrice bayesiene și procese gaussiene. Doctoratul său este de la Universitatea Duke și a publicat lucrări în NeurIPS, Cell, and Neuron.

Christopher Whitten este un dezvoltator de software în echipa JumpStart. El ajută la selectarea modelelor la scară și la integrarea modelelor cu alte servicii SageMaker. Chris este pasionat de accelerarea omniprezentei AI într-o varietate de domenii de afaceri.

Dr. Fabio Nonato de Paula este Senior Manager, Specialist GenAI SA, ajutând furnizorii de modele și clienții să scaleze AI generativă în AWS. Fabio are o pasiune pentru democratizarea accesului la tehnologia AI generativă. În afara serviciului, îl puteți găsi pe Fabio mergând cu motocicleta pe dealurile din Valea Sonoma sau citind ComiXology.

Dr. Ashish Khetan este un om de știință senior aplicat cu algoritmi încorporați Amazon SageMaker și ajută la dezvoltarea algoritmilor de învățare automată. Și-a luat doctoratul la Universitatea din Illinois Urbana-Champaign. Este un cercetător activ în învățarea automată și inferența statistică și a publicat multe lucrări în conferințele NeurIPS, ICML, ICLR, JMLR, ACL și EMNLP.

Karl Albertsen conduce produse, inginerie și știință pentru Amazon SageMaker Algorithms și JumpStart, centrul de învățare automată al SageMaker. Este pasionat de aplicarea învățării automate pentru a debloca valoarea afacerii.