Mixtral-8x7B je zdaj na voljo v Amazon SageMaker JumpStart | Spletne storitve 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)

Dobite naslednji izhod:

> 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)

Modeli Mixtral lahko zagotovijo razumevanje, kot je prikazano v naslednjem rezultatu z matematično logiko:

> 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.

Čiščenje

Ko končate z zagonom zvezka, izbrišite vse vire, ki ste jih ustvarili med postopkom, da se vaše zaračunavanje ustavi. Uporabite naslednjo kodo:

predictor.delete_model()
predictor.delete_endpoint()

V tej objavi smo vam pokazali, kako začeti uporabljati Mixtral-8x7B v SageMaker Studio in razmestiti model za sklepanje. Ker so osnovni modeli vnaprej usposobljeni, lahko pomagajo znižati stroške usposabljanja in infrastrukture ter omogočijo prilagoditev za vaš primer uporabe. Za začetek obiščite SageMaker JumpStart v SageMaker Studio.

viri

O avtorjih

Rachna Chadha je glavni arhitekt rešitev AI/ML v Strategic Accounts pri AWS. Rachna je optimist, ki verjame, da lahko etična in odgovorna uporaba umetne inteligence izboljša družbo v prihodnosti ter prinese gospodarsko in družbeno blaginjo. V prostem času Rachna rada preživlja čas z družino, hodi na pohode in posluša glasbo.

Dr. Kyle Ulrich je uporabni znanstvenik z Vgrajeni algoritmi Amazon SageMaker ekipa. Njegovi raziskovalni interesi vključujejo skalabilne algoritme strojnega učenja, računalniški vid, časovne vrste, Bayesove neparametrične in Gaussove procese. Njegov doktorat je pridobil na Univerzi Duke in je objavil članke v NeurIPS, Cell in Neuron.

Christopherja Whittena je razvijalec programske opreme v ekipi JumpStart. Pomaga pri prilagajanju izbire modela in integraciji modelov z drugimi storitvami SageMaker. Chris je navdušen nad pospeševanjem vseprisotnosti umetne inteligence na različnih poslovnih področjih.

Dr. Fabio Nonato de Paula je višji vodja specialista GenAI SA, ki ponudnikom modelov in strankam pomaga pri prilagajanju generativne umetne inteligence v AWS. Fabio ima strast do demokratizacije dostopa do generativne tehnologije umetne inteligence. Zunaj dela lahko najdete Fabia, ki se vozi z motorjem po hribih doline Sonoma ali bere ComiXology.

Dr. Ashish Khetan je višji aplikativni znanstvenik z vgrajenimi algoritmi Amazon SageMaker in pomaga pri razvoju algoritmov strojnega učenja. Doktoriral je na Univerzi Illinois Urbana-Champaign. Je aktiven raziskovalec strojnega učenja in statističnega sklepanja ter je objavil številne članke na konferencah NeurIPS, ICML, ICLR, JMLR, ACL in EMNLP.

Karl Albertsen vodi izdelke, inženiring in znanost za Amazon SageMaker Algorithms in JumpStart, SageMakerjevo vozlišče za strojno učenje. Navdušen je nad uporabo strojnega učenja za odklepanje poslovne vrednosti.