Mixtral-8x7B hiện có sẵn trong Amazon SageMaker JumpStart | Dịch vụ web của 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)

Bạn nhận được đầu ra sau:

> 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)

Các mô hình hỗn hợp có thể cung cấp khả năng hiểu như được hiển thị trong kết quả đầu ra sau đây với logic toán học:

> 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.

Làm sạch

Sau khi chạy xong sổ ghi chép, hãy xóa tất cả tài nguyên bạn đã tạo trong quá trình này để việc thanh toán của bạn dừng lại. Sử dụng mã sau đây:

predictor.delete_model()
predictor.delete_endpoint()

Trong bài đăng này, chúng tôi đã hướng dẫn bạn cách bắt đầu với Mixtral-8x7B trong SageMaker Studio và triển khai mô hình để suy luận. Vì các mô hình nền tảng được đào tạo trước nên chúng có thể giúp giảm chi phí đào tạo và cơ sở hạ tầng, đồng thời cho phép tùy chỉnh cho trường hợp sử dụng của bạn. Hãy truy cập SageMaker JumpStart trong SageMaker Studio ngay bây giờ để bắt đầu.

Thông tin

Giới thiệu về tác giả

rachna chadha là Kiến trúc sư giải pháp chính AI/ML trong Tài khoản chiến lược tại AWS. Rachna là một người lạc quan tin rằng việc sử dụng AI có đạo đức và có trách nhiệm có thể cải thiện xã hội trong tương lai và mang lại sự thịnh vượng về kinh tế và xã hội. Khi rảnh rỗi, Rachna thích dành thời gian cho gia đình, đi bộ đường dài và nghe nhạc.

Tiến sĩ Kyle Ulrich là một nhà khoa học ứng dụng với Các thuật toán tích hợp sẵn của Amazon SageMaker đội. Lĩnh vực nghiên cứu của ông bao gồm các thuật toán học máy có thể mở rộng, thị giác máy tính, chuỗi thời gian, phi tham số Bayesian và quy trình Gaussian. Tiến sĩ của anh ấy đến từ Đại học Duke và anh ấy đã xuất bản các bài báo trên NeurIPS, Cell và Neuron.

Christopher Whitten là nhà phát triển phần mềm trong nhóm JumpStart. Anh ấy giúp lựa chọn mô hình theo tỷ lệ và tích hợp các mô hình với các dịch vụ SageMaker khác. Chris rất đam mê việc thúc đẩy sự phổ biến của AI trên nhiều lĩnh vực kinh doanh khác nhau.

Tiến sĩ Fabio Nonato de Paula là Giám đốc cấp cao, Chuyên gia GenAI SA, giúp các nhà cung cấp mô hình và khách hàng mở rộng quy mô AI tổng hợp trong AWS. Fabio có niềm đam mê dân chủ hóa khả năng tiếp cận công nghệ AI sáng tạo. Ngoài giờ làm việc, bạn có thể thấy Fabio lái mô tô trên những ngọn đồi ở Thung lũng Sonoma hoặc đọc ComiXology.

Tiến sĩ Ashish Khetan là Nhà khoa học ứng dụng cấp cao với các thuật toán tích hợp Amazon SageMaker và giúp phát triển các thuật toán máy học. Ông lấy bằng Tiến sĩ tại Đại học Illinois Urbana-Champaign. Ông là một nhà nghiên cứu tích cực về học máy và suy luận thống kê, đồng thời đã xuất bản nhiều bài báo tại các hội nghị NeurIPS, ICML, ICLR, JMLR, ACL và EMNLP.

Karl Albertsen lãnh đạo sản phẩm, kỹ thuật và khoa học cho Thuật toán Amazon SageMaker và JumpStart, trung tâm máy học của SageMaker. Anh đam mê áp dụng công nghệ máy học để mở khóa giá trị kinh doanh.