Mixtral-8x7B এখন Amazon SageMaker JumpStart এ উপলব্ধ আমাজন ওয়েব সার্ভিসেস

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)

আপনি নিম্নলিখিত আউটপুট পাবেন:

> 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)

মিক্সট্রাল মডেলগুলি গণিতের যুক্তির সাথে নিম্নলিখিত আউটপুটে দেখানো হিসাবে উপলব্ধি প্রদান করতে পারে:

> 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.

পরিষ্কার কর

আপনি নোটবুক চালানো শেষ করার পরে, প্রক্রিয়াটিতে আপনার তৈরি করা সমস্ত সংস্থান মুছুন যাতে আপনার বিলিং বন্ধ হয়ে যায়। নিম্নলিখিত কোড ব্যবহার করুন:

predictor.delete_model()
predictor.delete_endpoint()

এই পোস্টে, আমরা আপনাকে দেখিয়েছি কিভাবে SageMaker স্টুডিওতে Mixtral-8x7B দিয়ে শুরু করতে হয় এবং অনুমানের জন্য মডেলটি স্থাপন করতে হয়। যেহেতু ফাউন্ডেশন মডেলগুলি প্রাক-প্রশিক্ষিত, তারা প্রশিক্ষণ এবং অবকাঠামো খরচ কমাতে সাহায্য করতে পারে এবং আপনার ব্যবহারের ক্ষেত্রে কাস্টমাইজেশন সক্ষম করতে পারে। শুরু করতে এখনই সেজমেকার স্টুডিওতে সেজমেকার জাম্পস্টার্ট দেখুন।

Resources

লেখক সম্পর্কে

রচনা চাদা AWS-এ স্ট্র্যাটেজিক অ্যাকাউন্টে একজন প্রধান সমাধান আর্কিটেক্ট এআই/এমএল। রচনা একজন আশাবাদী যিনি বিশ্বাস করেন যে AI এর নৈতিক ও দায়িত্বশীল ব্যবহার ভবিষ্যতে সমাজের উন্নতি করতে পারে এবং অর্থনৈতিক ও সামাজিক সমৃদ্ধি আনতে পারে। অবসর সময়ে, রচনা তার পরিবারের সাথে সময় কাটাতে, হাইকিং করতে এবং গান শুনতে পছন্দ করে।

ডাঃ কাইল উলরিচ সঙ্গে একজন ফলিত বিজ্ঞানী Amazon SageMaker বিল্ট-ইন অ্যালগরিদম টীম. তার গবেষণার আগ্রহের মধ্যে রয়েছে স্কেলযোগ্য মেশিন লার্নিং অ্যালগরিদম, কম্পিউটার ভিশন, টাইম সিরিজ, বায়েসিয়ান নন-প্যারামেট্রিক্স এবং গাউসিয়ান প্রক্রিয়া। তার পিএইচডি ডিউক বিশ্ববিদ্যালয় থেকে এবং তিনি নিউরিআইপিএস, সেল এবং নিউরনে গবেষণাপত্র প্রকাশ করেছেন।

ক্রিস্টোফার হুইটেন জাম্পস্টার্ট টিমের একজন সফটওয়্যার ডেভেলপার। তিনি মডেল নির্বাচন স্কেল এবং অন্যান্য SageMaker পরিষেবার সাথে মডেল একীভূত করতে সাহায্য করে। ক্রিস বিভিন্ন ব্যবসায়িক ডোমেন জুড়ে AI এর সর্বব্যাপীতাকে ত্বরান্বিত করার বিষয়ে উত্সাহী।

ডঃ ফ্যাবিও নোনাতো ডি পাওলা একজন সিনিয়র ম্যানেজার, বিশেষজ্ঞ GenAI SA, মডেল প্রদানকারী এবং গ্রাহকদের AWS-এ জেনারেটিভ AI স্কেল করতে সাহায্য করে। জেনারেটিভ এআই প্রযুক্তিতে অ্যাক্সেসকে গণতান্ত্রিক করার জন্য ফ্যাবিওর আবেগ রয়েছে। কাজের বাইরে, আপনি Sonoma ভ্যালির পাহাড়ে ফ্যাবিওকে তার মোটরসাইকেল চালাচ্ছেন বা ComiXology পড়তে দেখতে পাবেন।

আশিস খেতান ড অ্যামাজন সেজমেকার বিল্ট-ইন অ্যালগরিদম সহ একজন সিনিয়র ফলিত বিজ্ঞানী এবং মেশিন লার্নিং অ্যালগরিদম বিকাশে সহায়তা করে। তিনি ইউনিভার্সিটি অফ ইলিনয় আরবানা-চ্যাম্পেইন থেকে পিএইচডি লাভ করেন। তিনি মেশিন লার্নিং এবং পরিসংখ্যানগত অনুমানে একজন সক্রিয় গবেষক এবং নিউরিআইপিএস, আইসিএমএল, আইসিএলআর, জেএমএলআর, এসিএল এবং ইএমএনএলপি সম্মেলনে অনেক গবেষণাপত্র প্রকাশ করেছেন।

কার্ল অ্যালবার্টসেন Amazon SageMaker Algorithms এবং JumpStart, SageMaker-এর মেশিন লার্নিং হাব-এর জন্য পণ্য, প্রকৌশল এবং বিজ্ঞানের নেতৃত্ব দেয়৷ ব্যবসার মূল্য আনলক করার জন্য তিনি মেশিন লার্নিং প্রয়োগ করার বিষয়ে উত্সাহী।