이제 Amazon SageMaker JumpStart에서 Mixtral-8x7B를 사용할 수 있습니다 | 아마존 웹 서비스

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)

다음과 같은 결과가 나타납니다.

> 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)

Mixtral 모델은 수학 논리를 사용하여 다음 출력에 표시된 대로 이해력을 제공할 수 있습니다.

> 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.

정리

노트북 실행을 마친 후 해당 프로세스에서 생성한 모든 리소스를 삭제하면 요금 청구가 중지됩니다. 다음 코드를 사용하세요.

predictor.delete_model()
predictor.delete_endpoint()

이 게시물에서는 SageMaker Studio에서 Mixtral-8x7B를 시작하고 추론을 위해 모델을 배포하는 방법을 보여주었습니다. 기초 모델은 사전 훈련되어 있으므로 훈련 및 인프라 비용을 낮추고 사용 사례에 맞게 사용자 정의할 수 있습니다. 지금 SageMaker Studio에서 SageMaker JumpStart를 방문하여 시작하세요.

제품 자료

저자 소개

라크나 차다 AWS Strategic Accounts의 수석 솔루션 아키텍트 AI/ML입니다. Rachna는 AI의 윤리적이고 책임 있는 사용이 미래의 사회를 개선하고 경제 및 사회적 번영을 가져올 수 있다고 믿는 낙관론자입니다. 여가 시간에 Rachna는 가족과 함께 시간을 보내고, 하이킹을 하고, 음악을 듣는 것을 좋아합니다.

카일 울리히 박사 는 응용 과학자입니다. Amazon SageMaker 내장 알고리즘 팀. 그의 연구 관심사는 확장 가능한 기계 학습 알고리즘, 컴퓨터 비전, 시계열, 베이지안 비모수 및 가우시안 프로세스를 포함합니다. Duke University에서 박사 학위를 받았으며 NeurIPS, Cell 및 Neuron에 논문을 발표했습니다.

크리스토퍼 휘튼 JumpStart 팀의 소프트웨어 개발자입니다. 그는 모델 선택을 확장하고 모델을 다른 SageMaker 서비스와 통합하는 데 도움을 줍니다. Chris는 다양한 비즈니스 영역에서 AI의 편재성을 가속화하는 데 열정을 쏟고 있습니다.

파비오 노나토 데 파울라 박사 그는 모델 공급자와 고객이 AWS에서 생성 AI를 확장하도록 돕는 전문가 GenAI SA의 수석 관리자입니다. Fabio는 생성적 AI 기술에 대한 접근을 민주화하는 데 열정을 갖고 있습니다. 직장 밖에서는 파비오가 소노마 밸리 언덕에서 오토바이를 타거나 코믹솔로지(ComiXology)를 읽는 모습을 볼 수 있습니다.

Ashish Khetan 박사 Amazon SageMaker 내장 알고리즘을 사용하는 수석 응용 과학자이며 기계 학습 알고리즘 개발을 돕습니다. 그는 University of Illinois Urbana-Champaign에서 박사 학위를 받았습니다. 그는 기계 학습 및 통계적 추론 분야에서 활동적인 연구원이며 NeurIPS, ICML, ICLR, JMLR, ACL 및 EMNLP 컨퍼런스에서 많은 논문을 발표했습니다.

칼 알베르센 Amazon SageMaker 알고리즘 및 SageMaker의 기계 학습 허브인 JumpStart의 제품, 엔지니어링 및 과학을 이끌고 있습니다. 그는 기계 학습을 적용하여 비즈니스 가치를 창출하는 데 열정적입니다.