Mixtral-8x7B 现已在 Amazon SageMaker JumpStart 中提供 |亚马逊网络服务

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)

您将获得以下输出：

> 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)

混合模型可以通过数学逻辑提供理解，如以下输出所示：

> 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.

清理

运行完笔记本后，删除在此过程中创建的所有资源，以便停止计费。使用以下代码：

predictor.delete_model()
predictor.delete_endpoint()

在这篇文章中，我们向您展示了如何在 SageMaker Studio 中开始使用 Mixtral-8x7B 并部署模型进行推理。由于基础模型是预先训练的，因此它们可以帮助降低培训和基础设施成本，并支持针对您的用例进行定制。立即访问 SageMaker Studio 中的 SageMaker JumpStart 以开始使用。

资源

关于作者

拉奇纳查达 是 AWS 战略客户的首席解决方案架构师 AI/ML。 Rachna 是一个乐观主义者，他相信以合乎道德和负责任的方式使用 AI 可以改善未来的社会并带来经济和社会繁荣。 在业余时间，Rachna 喜欢与家人共度时光、远足和听音乐。

凯尔乌尔里希博士 是一名应用科学家 Amazon SageMaker 内置算法 团队。 他的研究兴趣包括可扩展机器学习算法、计算机视觉、时间序列、贝叶斯非参数和高斯过程。 他在杜克大学获得博士学位，并在 NeurIPS、Cell 和 Neuron 上发表了论文。

克里斯托弗·惠顿 是 JumpStart 团队的软件开发人员。他帮助扩展模型选择并将模型与其他 SageMaker 服务集成。 Chris 热衷于加速人工智能在各个业务领域的普及。

法比奥·诺纳托·德保拉博士 是 GenAI SA 专家的高级经理，帮助模型提供商和客户在 AWS 中扩展生成式 AI。 Fabio 热衷于实现生成式人工智能技术的民主化。工作之余，您会发现法比奥 (Fabio) 骑着摩托车在索诺玛山谷的山上行走，或者阅读 ComiXology。

Ashish Khetan 博士 是 Amazon SageMaker 内置算法的高级应用科学家，帮助开发机器学习算法。 他在伊利诺伊大学香槟分校获得博士学位。 他是机器学习和统计推理领域的活跃研究者，在 NeurIPS、ICML、ICLR、JMLR、ACL 和 EMNLP 会议上发表了多篇论文。

卡尔艾伯森 领导 Amazon SageMaker 算法和 JumpStart（SageMaker 的机器学习中心）的产品、工程和科学。 他热衷于应用机器学习来释放商业价值。