मिक्सट्रल-8x7बी अब अमेज़न सेजमेकर जम्पस्टार्ट | पर उपलब्ध है अमेज़न वेब सेवाएँ

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)

आपको निम्न आउटपुट मिलते हैं:

> 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)

मिक्सट्रल मॉडल समझ प्रदान कर सकते हैं जैसा कि गणित तर्क के साथ निम्नलिखित आउटपुट में दिखाया गया है:

> 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.

क्लीन अप

नोटबुक चलाने के बाद, इस प्रक्रिया में आपके द्वारा बनाए गए सभी संसाधनों को हटा दें ताकि आपकी बिलिंग रोक दी जाए। निम्नलिखित कोड का प्रयोग करें:

predictor.delete_model()
predictor.delete_endpoint()

इस पोस्ट में, हमने आपको दिखाया कि सेजमेकर स्टूडियो में मिक्सट्रल-8x7बी के साथ कैसे शुरुआत करें और अनुमान के लिए मॉडल को कैसे तैनात करें। क्योंकि फाउंडेशन मॉडल पूर्व-प्रशिक्षित होते हैं, वे प्रशिक्षण और बुनियादी ढांचे की लागत को कम करने और आपके उपयोग के मामले में अनुकूलन को सक्षम करने में मदद कर सकते हैं। आरंभ करने के लिए अभी सेजमेकर स्टूडियो में सेजमेकर जम्पस्टार्ट पर जाएँ।

उपयुक्त संसाधन चुनें

लेखक के बारे में

रचना चड्ढा एडब्ल्यूएस में सामरिक खातों में प्रधान समाधान वास्तुकार एआई/एमएल है। रचना एक आशावादी है जो मानती है कि एआई का नैतिक और जिम्मेदार उपयोग भविष्य में समाज को बेहतर बना सकता है और आर्थिक और सामाजिक समृद्धि ला सकता है। अपने खाली समय में, रचना को अपने परिवार के साथ समय बिताना, लंबी पैदल यात्रा करना और संगीत सुनना पसंद है।

डॉ काइल उलरिच के साथ एक अनुप्रयुक्त वैज्ञानिक है अमेज़ॅन सेजमेकर बिल्ट-इन एल्गोरिदम टीम। उनके शोध के हितों में स्केलेबल मशीन लर्निंग एल्गोरिदम, कंप्यूटर विज़न, टाइम सीरीज़, बायेसियन नॉन-पैरामेट्रिक्स और गॉसियन प्रोसेस शामिल हैं। उनकी पीएचडी ड्यूक यूनिवर्सिटी से है और उन्होंने न्यूरआईपीएस, सेल और न्यूरॉन में पत्र प्रकाशित किए हैं।

क्रिस्टोफर व्हिटेन जम्पस्टार्ट टीम में एक सॉफ्टवेयर डेवलपर है। वह मॉडल चयन को स्केल करने और अन्य सेजमेकर सेवाओं के साथ मॉडल को एकीकृत करने में मदद करता है। क्रिस को विभिन्न व्यावसायिक क्षेत्रों में एआई की सर्वव्यापकता में तेजी लाने का शौक है।

डॉ. फैबियो नोनाटो डी पाउला एक वरिष्ठ प्रबंधक, विशेषज्ञ जेनएआई एसए हैं, जो मॉडल प्रदाताओं और ग्राहकों को एडब्ल्यूएस में जेनरेटर एआई बढ़ाने में मदद करते हैं। फैबियो को जेनरेटिव एआई तकनीक तक पहुंच को लोकतांत्रिक बनाने का जुनून है। काम के अलावा, आप फैबियो को सोनोमा घाटी की पहाड़ियों में अपनी मोटरसाइकिल चलाते या कॉमिक्सोलॉजी पढ़ते हुए पा सकते हैं।

डॉ आशीष खेतानी Amazon SageMaker बिल्ट-इन एल्गोरिदम के साथ एक वरिष्ठ एप्लाइड साइंटिस्ट हैं और मशीन लर्निंग एल्गोरिदम विकसित करने में मदद करते हैं। उन्होंने इलिनोइस विश्वविद्यालय उरबाना-शैंपेन से पीएचडी की उपाधि प्राप्त की। वह मशीन लर्निंग और सांख्यिकीय अनुमान में एक सक्रिय शोधकर्ता हैं, और उन्होंने NeurIPS, ICML, ICLR, JMLR, ACL और EMNLP सम्मेलनों में कई पत्र प्रकाशित किए हैं।

कार्ल अल्बर्टसन अमेज़ॅन सेजमेकर एल्गोरिदम और जम्पस्टार्ट, सेजमेकर के मशीन लर्निंग हब के लिए उत्पाद, इंजीनियरिंग और विज्ञान का नेतृत्व करता है। उन्हें व्यावसायिक मूल्य को अनलॉक करने के लिए मशीन लर्निंग लागू करने का शौक है।