जनरेटिव डेटा इंटेलिजेंस

डेटाब्रिक्स डीबीआरएक्स अब अमेज़ॅन सेजमेकर जम्पस्टार्ट | पर उपलब्ध है अमेज़न वेब सेवाएँ

दिनांक:

आज, हमें यह घोषणा करते हुए खुशी हो रही है कि डीबीआरएक्स मॉडल, द्वारा विकसित एक खुला, सामान्य प्रयोजन वाला बड़ा भाषा मॉडल (एलएलएम)। डाटब्रिक्सके माध्यम से ग्राहकों के लिए उपलब्ध है अमेज़न SageMaker जम्पस्टार्ट चालू अनुमान के लिए एक क्लिक से तैनात करना। डीबीआरएक्स एलएलएम एक बारीक-बारीक मिश्रण-विशेषज्ञों (एमओई) आर्किटेक्चर को नियोजित करता है, जो सावधानीपूर्वक क्यूरेटेड डेटा के 12 ट्रिलियन टोकन और 32,000 टोकन की अधिकतम संदर्भ लंबाई पर पूर्व-प्रशिक्षित है।

आप इस मॉडल को सेजमेकर जंपस्टार्ट, एक मशीन लर्निंग (एमएल) हब के साथ आज़मा सकते हैं जो एल्गोरिदम और मॉडल तक पहुंच प्रदान करता है ताकि आप जल्दी से एमएल के साथ शुरुआत कर सकें। इस पोस्ट में, हम DBRX मॉडल को खोजने और तैनात करने के तरीके के बारे में जानेंगे।

डीबीआरएक्स मॉडल क्या है

डीबीआरएक्स ट्रांसफॉर्मर आर्किटेक्चर पर निर्मित एक परिष्कृत डिकोडर-केवल एलएलएम है। यह एक बारीक MoE आर्किटेक्चर का उपयोग करता है, जिसमें 132 बिलियन कुल पैरामीटर शामिल होते हैं, इनमें से 36 बिलियन पैरामीटर किसी भी दिए गए इनपुट के लिए सक्रिय होते हैं।

मॉडल को टेक्स्ट और कोड के 12 ट्रिलियन टोकन वाले डेटासेट का उपयोग करके पूर्व-प्रशिक्षण दिया गया। मिक्सट्रल और ग्रोक-1 जैसे अन्य खुले एमओई मॉडलों के विपरीत, डीबीआरएक्स में अनुकूलित प्रदर्शन के लिए अधिक मात्रा में छोटे विशेषज्ञों का उपयोग करते हुए एक सुक्ष्म दृष्टिकोण की सुविधा है। अन्य MoE मॉडलों की तुलना में, DBRX में 16 विशेषज्ञ हैं और 4 को चुनते हैं।

मॉडल को डेटाब्रिक्स ओपन मॉडल लाइसेंस के तहत बिना किसी प्रतिबंध के उपयोग के लिए उपलब्ध कराया गया है।

सेजमेकर जम्पस्टार्ट क्या है?

सेजमेकर जंपस्टार्ट एक पूरी तरह से प्रबंधित मंच है जो सामग्री लेखन, कोड निर्माण, प्रश्न उत्तर, कॉपी राइटिंग, सारांश, वर्गीकरण और सूचना पुनर्प्राप्ति जैसे विभिन्न उपयोग मामलों के लिए अत्याधुनिक फाउंडेशन मॉडल प्रदान करता है। यह पूर्व-प्रशिक्षित मॉडलों का एक संग्रह प्रदान करता है जिन्हें आप एमएल अनुप्रयोगों के विकास और तैनाती में तेजी लाते हुए जल्दी और आसानी से तैनात कर सकते हैं। सेजमेकर जम्पस्टार्ट के प्रमुख घटकों में से एक मॉडल हब है, जो विभिन्न कार्यों के लिए डीबीआरएक्स जैसे पूर्व-प्रशिक्षित मॉडलों की एक विशाल सूची प्रदान करता है।

अब आप कुछ ही क्लिक में डीबीआरएक्स मॉडल खोज और तैनात कर सकते हैं अमेज़ॅन सैजमेकर स्टूडियो या सेजमेकर पायथन एसडीके के माध्यम से प्रोग्रामेटिक रूप से, आपको मॉडल प्रदर्शन और एमएलओपीएस नियंत्रण प्राप्त करने में सक्षम बनाता है अमेज़न SageMaker जैसे सुविधाएँ अमेज़न SageMaker पाइपलाइन, अमेज़न SageMaker डिबगर, या कंटेनर लॉग। मॉडल को AWS सुरक्षित वातावरण में और आपके VPC नियंत्रण में तैनात किया गया है, जो डेटा सुरक्षा प्रदान करने में मदद करता है।

सेजमेकर जम्पस्टार्ट में मॉडल खोजें

आप सेजमेकर स्टूडियो यूआई और सेजमेकर पायथन एसडीके में सेजमेकर जम्पस्टार्ट के माध्यम से डीबीआरएक्स मॉडल तक पहुंच सकते हैं। इस अनुभाग में, हम सेजमेकर स्टूडियो में मॉडलों की खोज कैसे करें, इसके बारे में जानेंगे।

सेजमेकर स्टूडियो एक एकीकृत विकास वातावरण (आईडीई) है जो एकल वेब-आधारित विज़ुअल इंटरफ़ेस प्रदान करता है जहां आप डेटा तैयार करने से लेकर निर्माण, प्रशिक्षण और अपने एमएल मॉडल को तैनात करने तक सभी एमएल विकास चरणों को करने के लिए उद्देश्य-निर्मित टूल तक पहुंच सकते हैं। सेजमेकर स्टूडियो कैसे शुरू करें और स्थापित करें, इसके बारे में अधिक जानकारी के लिए देखें अमेज़ॅन सैजमेकर स्टूडियो.

सेजमेकर स्टूडियो में, आप चुनकर सेजमेकर जम्पस्टार्ट तक पहुंच सकते हैं कूदना शुरू करो नेविगेशन फलक में

सेजमेकर जम्पस्टार्ट लैंडिंग पृष्ठ से, आप खोज बॉक्स में "डीबीआरएक्स" खोज सकते हैं। खोज परिणाम सूचीबद्ध होंगे डीबीआरएक्स निर्देश और डीबीआरएक्स बेस.

आप मॉडल के बारे में विवरण देखने के लिए मॉडल कार्ड चुन सकते हैं जैसे लाइसेंस, प्रशिक्षण के लिए उपयोग किया गया डेटा और मॉडल का उपयोग कैसे करें। आपको यह भी मिलेगा तैनाती मॉडल को तैनात करने और एक समापन बिंदु बनाने के लिए बटन।

मॉडल को सेजमेकर जम्पस्टार्ट में तैनात करें

जब आप चुनते हैं तो परिनियोजन प्रारंभ हो जाता है तैनाती बटन। परिनियोजन समाप्त होने के बाद, आप देखेंगे कि एक समापन बिंदु बन गया है। आप नमूना अनुमान अनुरोध पेलोड पास करके या एसडीके का उपयोग करके परीक्षण विकल्प का चयन करके समापन बिंदु का परीक्षण कर सकते हैं। जब आप एसडीके का उपयोग करने का विकल्प चुनते हैं, तो आपको उदाहरण कोड दिखाई देगा जिसे आप सेजमेकर स्टूडियो में अपनी पसंद के नोटबुक संपादक में उपयोग कर सकते हैं।

डीबीआरएक्स बेस

एसडीके का उपयोग करके तैनात करने के लिए, हम द्वारा निर्दिष्ट डीबीआरएक्स बेस मॉडल का चयन करके शुरुआत करते हैं model_id वैल्यू हगिंगफेस-एलएलएम-डीबीआरएक्स-बेस के साथ। आप निम्नलिखित कोड के साथ सेजमेकर पर किसी भी चयनित मॉडल को तैनात कर सकते हैं। इसी तरह, आप DBRX इंस्ट्रक्शन को उसकी अपनी मॉडल आईडी का उपयोग करके तैनात कर सकते हैं।

from sagemaker.jumpstart.model import JumpStartModel

accept_eula = True

model = JumpStartModel(model_id="huggingface-llm-dbrx-base")
predictor = model.deploy(accept_eula=accept_eula)

यह मॉडल को सेजमेकर पर डिफ़ॉल्ट कॉन्फ़िगरेशन के साथ तैनात करता है, जिसमें डिफ़ॉल्ट इंस्टेंस प्रकार और डिफ़ॉल्ट वीपीसी कॉन्फ़िगरेशन शामिल हैं। आप गैर-डिफ़ॉल्ट मान निर्दिष्ट करके इन कॉन्फ़िगरेशन को बदल सकते हैं जम्पस्टार्टमॉडल. अंतिम-उपयोगकर्ता लाइसेंस समझौते (ईयूएलए) को स्वीकार करने के लिए यूला मान को स्पष्ट रूप से सत्य के रूप में परिभाषित किया जाना चाहिए। यह भी सुनिश्चित करें कि आपके पास एक या अधिक उदाहरणों के रूप में एंडपॉइंट उपयोग के लिए ml.p4d.24xlarge या ml.pde.24xlarge का उपयोग करने के लिए खाता-स्तरीय सेवा सीमा है। आप निर्देशों का पालन कर सकते हैं यहाँ उत्पन्न करें सेवा कोटा बढ़ाने का अनुरोध करने के लिए।

इसे तैनात करने के बाद, आप सेजमेकर भविष्यवक्ता के माध्यम से तैनात समापन बिंदु के खिलाफ अनुमान चला सकते हैं:

payload = {
    "inputs": "Hello!",
    "parameters": {
        "max_new_tokens": 10,
    },
}
predictor.predict(payload)

उदाहरण संकेत देता है

आप किसी भी मानक टेक्स्ट जेनरेशन मॉडल की तरह डीबीआरएक्स बेस मॉडल के साथ इंटरैक्ट कर सकते हैं, जहां मॉडल एक इनपुट अनुक्रम को संसाधित करता है और अनुक्रम में अगले शब्दों की भविष्यवाणी करता है। इस अनुभाग में, हम कुछ उदाहरण संकेत और नमूना आउटपुट प्रदान करते हैं।

कोड पीढ़ी

पिछले उदाहरण का उपयोग करके, हम कोड जनरेशन प्रॉम्प्ट का उपयोग इस प्रकार कर सकते हैं:

payload = { 
      "inputs": "Write a function to read a CSV file in Python using pandas library:", 
      "parameters": { 
          "max_new_tokens": 30, }, } 
           response = predictor.predict(payload)["generated_text"].strip() 
           print(response)

निम्नलिखित आउटपुट है:

import pandas as pd 
df = pd.read_csv("file_name.csv") 
#The above code will import pandas library and then read the CSV file using read_csv

भावनाओं का विश्लेषण

आप डीबीआरएक्स के साथ निम्नलिखित संकेत का उपयोग करके भावना विश्लेषण कर सकते हैं:

payload = {
"inputs": """
Tweet: "I am so excited for the weekend!"
Sentiment: Positive

Tweet: "Why does traffic have to be so terrible?"
Sentiment: Negative

Tweet: "Just saw a great movie, would recommend it."
Sentiment: Positive

Tweet: "According to the weather report, it will be cloudy today."
Sentiment: Neutral

Tweet: "This restaurant is absolutely terrible."
Sentiment: Negative

Tweet: "I love spending time with my family."
Sentiment:""",
"parameters": {
"max_new_tokens": 2,
},
}
response = predictor.predict(payload)["generated_text"].strip()
print(response)

निम्नलिखित आउटपुट है:

सवाल जवाब

आप डीबीआरएक्स के साथ निम्नलिखित जैसे प्रश्न उत्तर संकेत का उपयोग कर सकते हैं:

# Question answering
payload = {
    "inputs": "Respond to the question: How did the development of transportation systems, such as railroads and steamships, impact global trade and cultural exchange?",
    "parameters": {
        "max_new_tokens": 225,
    },
}
response = predictor.predict(payload)["generated_text"].strip()
print(response)

निम्नलिखित आउटपुट है:

The development of transportation systems, such as railroads and steamships, impacted global trade and cultural exchange in a number of ways. 
The documents provided show that the development of these systems had a profound effect on the way people and goods were able to move around the world. 
One of the most significant impacts of the development of transportation systems was the way it facilitated global trade. 
The documents show that the development of railroads and steamships made it possible for goods to be transported more quickly and efficiently than ever before. 
This allowed for a greater exchange of goods between different parts of the world, which in turn led to a greater exchange of ideas and cultures. 
Another impact of the development of transportation systems was the way it facilitated cultural exchange. The documents show that the development of railroads and steamships made it possible for people to travel more easily and quickly than ever before. 
This allowed for a greater exchange of ideas and cultures between different parts of the world. Overall, the development of transportation systems, such as railroads and steamships, had a profound impact on global trade and cultural exchange.

डीबीआरएक्स निर्देश

डीबीआरएक्स का निर्देश-ट्यून किया गया संस्करण स्वरूपित निर्देशों को स्वीकार करता है जहां वार्तालाप भूमिकाएं उपयोगकर्ता के संकेत के साथ शुरू होनी चाहिए और उपयोगकर्ता निर्देशों और सहायक (डीबीआरएक्स-निर्देश) के बीच वैकल्पिक होनी चाहिए। निर्देश प्रारूप का कड़ाई से सम्मान किया जाना चाहिए, अन्यथा मॉडल इष्टतम आउटपुट उत्पन्न करेगा। इंस्ट्रक्शन मॉडल के लिए प्रॉम्प्ट बनाने का टेम्प्लेट इस प्रकार परिभाषित किया गया है:

<|im_start|>system
{system_message} <|im_end|>
<|im_start|>user
{human_message} <|im_end|>
<|im_start|>assistantn

<|im_start|> और <|im_end|> स्ट्रिंग की शुरुआत (बीओएस) और स्ट्रिंग के अंत (ईओएस) के लिए विशेष टोकन हैं। मॉडल में सिस्टम, उपयोगकर्ता और सहायक के बीच कई वार्तालाप मोड़ हो सकते हैं, जिससे मॉडल की प्रतिक्रियाओं को बढ़ाने के लिए कुछ-शॉट उदाहरणों को शामिल करने की अनुमति मिलती है।

निम्नलिखित कोड दिखाता है कि आप प्रॉम्प्ट को निर्देश प्रारूप में कैसे प्रारूपित कर सकते हैं:

from typing import Dict, List

def format_instructions(instructions: List[Dict[str, str]]) -> List[str]:
    """Format instructions where conversation roles must alternate system/user/assistant/user/assistant/..."""
    prompt: List[str] = []
    for instruction in instructions:
        if instruction["role"] == "system":
            prompt.extend(["<|im_start|>systemn", (instruction["content"]).strip(), " <|im_end|>n"])
        elif instruction["role"] == "user":
            prompt.extend(["<|im_start|>usern", (instruction["content"]).strip(), " <|im_end|>n"])
        else:
            raise ValueError(f"Invalid role: {instruction['role']}. Role must be either 'user' or 'system'.")
    prompt.extend(["<|im_start|>assistantn"])
    return "".join(prompt)

def print_instructions(prompt: str, response: str) -> None:
    bold, unbold = '33[1m', '33[0m'
    print(f"{bold}> Input{unbold}n{prompt}nn{bold}> Output{unbold}n{response['generated_text'].strip()}n")

ज्ञान पुनर्प्राप्ति

आप ज्ञान पुनर्प्राप्ति के लिए निम्नलिखित संकेत का उपयोग कर सकते हैं:

instructions = [
{"role": "system", "content": "You are an expert in suggesting diet plans optimized for different sports or fitness activities, taking into account energy requirements, and recovery requirements."},
{"role": "user", "content": "I am trying to build muscle mass and increase my strength. What kind of high-protein, calorie-dense diet plan would you recommend for me?"}
]
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 700, "temperature": 0.5, "do_sample": True}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

निम्नलिखित आउटपुट है:

> Input
<|im_start|>system
You are an expert in suggesting diet plans optimized for different sports or fitness activities, taking into account energy requirements, and recovery requirements. <|im_end|>
<|im_start|>user
I am trying to build muscle mass and increase my strength. What kind of high-protein, calorie-dense diet plan would you recommend for me? <|im_end|>
<|im_start|>assistant

> Output
Absolutely, I'd be happy to help you with that. Given your goal of building muscle mass and increasing strength, you'll want a diet that's high in protein and provides sufficient calories to support muscle growth and recovery. Here's a basic outline of what your diet plan could look like:

1. **Breakfast:**
   - 3 whole eggs
   - 3 egg whites
   - 1 cup of oatmeal
   - 1 scoop of whey protein
   - 1 banana

2. **Mid-Morning Snack:**
   - 1.5 ounces of almonds
   - 1 apple

3. **Lunch:**
   - 8 ounces of chicken breast
   - 1 cup of brown rice
   - 1 cup of mixed vegetables

4. **Afternoon Snack:**
   - 1.5 cups of Greek yogurt
   - 1 cup of mixed berries

5. **Dinner:**
   - 8 ounces of salmon or lean beef
   - 1 cup of quinoa
   - 1.5 cups of mixed vegetables

6. **Evening Snack:**
   - 1 scoop of casein protein
   - 1 tablespoon of almond butter

This is a high-protein, calorie-dense diet that includes a variety of nutrient-rich foods. It's important to note that everyone's nutritional needs are different, so you may need to adjust portion sizes or food choices based on your specific needs and preferences.

Also, remember to stay hydrated by drinking plenty of water throughout the day. Regular exercise, particularly strength training, is crucial to achieving your goals. It's also important to get enough sleep to aid in muscle recovery and growth.

Before starting any new diet or exercise program, it's a good idea to consult with a healthcare professional or a registered dietitian. They can provide personalized advice based on your health history and current lifestyle.

कोड पीढ़ी

डीबीआरएक्स मॉडल कोडिंग कार्यों के लिए बेंचमार्क ताकत प्रदर्शित करते हैं। उदाहरण के लिए, निम्नलिखित कोड देखें:

instructions = [ 
{"role": "system", "content": "You are an expert in coding and programming. Your role is to provide examples, explanations, and insights related to programming languages, algorithms, data structures, and software development practices."}, 
{"role": "user", "content": "Write a Python script to read a CSV file containing stock prices and plot the closing prices over time using Matplotlib."} 
] 
prompt = format_instructions(instructions) 
payload = { "inputs": prompt, "parameters": {"max_new_tokens": 315, "temperature": 0.3, "do_sample": True} } 
response=predictor.predict(payload) 
print_instructions(prompt, response)

निम्नलिखित आउटपुट है:

> Input
<|im_start|>system
You are an expert in coding and programming. Your role is to provide examples, explanations, and insights related to programming languages, algorithms, data structures, and software development practices. <|im_end|>
<|im_start|>user
Write a Python script to read a CSV file containing stock prices and plot the closing prices over time using Matplotlib. <|im_end|>
<|im_start|>assistant

> Output
Sure, I'd be happy to help you with that. Here's a simple Python script that uses the `pandas` library to read a CSV file and `matplotlib` to plot the closing prices over time.

```python
import pandas as pd
import matplotlib.pyplot as plt

# Load the data from a CSV file
df = pd.read_csv('stock_prices.csv')

# Plot the closing prices over time
plt.figure(figsize=(12,5))
plt.plot(df['Date'], df['Close'])
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Stock Prices Over Time')
plt.show()
```

In this script, replace `'stock_prices.csv'` with the path to your CSV file. The file should have columns named 'Date' and 'Close' for this script to work correctly. If your file uses different column names, you'll need to adjust the script accordingly.

The `pandas` library is a powerful tool for data manipulation and analysis. It can read data from a variety of sources, including CSV files, and represent the data in a tabular format. The `matplotlib` library is a popular choice for creating static, animated, and interactive visualizations in Python.

This script first loads the data from the CSV file into a pandas DataFrame. It then plots the 'Close' column against the 'Date' column using matplotlib's `plot()` function. The `figure()` function is used to specify the size of the plot, and `show()` is used to display the plot.

गणित और तर्क

डीबीआरएक्स मॉडल गणितीय सटीकता में ताकत की भी रिपोर्ट करते हैं। उदाहरण के लिए, निम्नलिखित कोड देखें:

instructions = [
  {"role": "system", "content": "You are an expert in mathematics and reasoning. Your role is to provide examples, explanations, and insights related to mathematical concepts, problem-solving techniques, and logical reasoning."},
  {"role": "user", "content": "A car rental company charges $40 per day plus $0.25 per mile driven. If I rented a car for 3 days and drove 250 miles, what would be the total cost? Break down the calculation steps before giving the final answer."}
]
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 400, "temperature": 0.2, "do_sample": True}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

डीबीआरएक्स समझ प्रदान कर सकता है जैसा कि गणित तर्क के साथ निम्नलिखित आउटपुट में दिखाया गया है:

> Input
<|im_start|>system
You are an expert in mathematics and reasoning. Your role is to provide examples, explanations, and insights related to mathematical concepts, problem-solving techniques, and logical reasoning. <|im_end|>
<|im_start|>user
A car rental company charges $40 per day plus $0.25 per mile driven. If I rented a car for 3 days and drove 250 miles, what would be the total cost? Break down the calculation steps before giving the final answer. <|im_end|>
<|im_start|>assistant

> Output
Sure, I'd be happy to help with that! The problem you've presented involves both fixed costs (the daily rate) and variable costs (the cost per mile). Let's break it down:

1. First, let's calculate the total cost of the fixed daily rate. The car rental company charges $40 per day, and you rented the car for 3 days. So, the total cost for the daily rate is $40/day * 3 days = $120.

2. Next, let's calculate the total cost of the variable rate, which is the cost per mile driven. The company charges $0.25 per mile, and you drove 250 miles. So, the total cost for the mileage is $0.25/mile * 250 miles = $62.50.

3. Finally, to find the total cost of renting the car, we add the total cost of the daily rate and the total cost of the mileage. So, the total cost is $120 + $62.50 = $182.50.

So, the total cost of renting the car for 3 days and driving 250 miles would be $182.50.

क्लीन अप

नोटबुक चलाने के बाद, सुनिश्चित करें कि आपने इस प्रक्रिया में बनाए गए सभी संसाधनों को हटा दिया है ताकि आपकी बिलिंग रोक दी जाए। निम्नलिखित कोड का प्रयोग करें:

predictor.delete_model()
predictor.delete_endpoint()

निष्कर्ष

इस पोस्ट में, हमने आपको दिखाया कि सेजमेकर स्टूडियो में डीबीआरएक्स 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

शिखर क्वात्र अमेज़ॅन वेब सर्विसेज में एआई/एमएल स्पेशलिस्ट सॉल्यूशंस आर्किटेक्ट हैं, जो एक अग्रणी ग्लोबल सिस्टम इंटीग्रेटर के साथ काम करते हैं। उन्होंने एआई/एमएल और आईओटी डोमेन में 400 से अधिक पेटेंट के साथ सबसे कम उम्र के भारतीय मास्टर आविष्कारकों में से एक का खिताब अर्जित किया है। उनके पास स्टार्टअप से लेकर बड़े पैमाने के उद्यमों तक, IoT रिसर्च इंजीनियर, डेटा साइंटिस्ट से लेकर डेटा और एआई आर्किटेक्ट तक उद्योग का 8 वर्षों से अधिक का अनुभव है। शिखर संगठनों के लिए लागत-कुशल, स्केलेबल क्लाउड वातावरण की वास्तुकला, निर्माण और रखरखाव में सहायता करता है और रणनीतिक उद्योग के निर्माण में जीएसआई भागीदारों का समर्थन करता है।

निथियं विजयेश्वरन AWS में सॉल्यूशन आर्किटेक्ट हैं। उनका फोकस क्षेत्र जेनरेटिव एआई और एडब्ल्यूएस एआई एक्सेलेरेटर है। उनके पास कंप्यूटर विज्ञान और जैव सूचना विज्ञान में स्नातक की डिग्री है। Niithiyn AWS ग्राहकों को कई मोर्चों पर सक्षम बनाने और जेनरेटिव AI को अपनाने में तेजी लाने के लिए जेनरेटिव AI GTM टीम के साथ मिलकर काम करता है। वह डलास मावेरिक्स का शौक़ीन प्रशंसक है और उसे स्नीकर्स इकट्ठा करने में मज़ा आता है।

सेबस्टियन बुस्टिलो AWS में सॉल्यूशन आर्किटेक्ट हैं। वह जेनरेटिव एआई और कंप्यूट एक्सेलेरेटर के प्रति गहन जुनून के साथ एआई/एमएल प्रौद्योगिकियों पर ध्यान केंद्रित करता है। AWS में, वह ग्राहकों को जेनरेटिव AI के माध्यम से व्यावसायिक मूल्य अनलॉक करने में मदद करता है। जब वह काम पर नहीं होता है, तो वह एक बेहतरीन कप विशेष कॉफी बनाने और अपनी पत्नी के साथ दुनिया की खोज करने का आनंद लेता है।

अरमांडो डियाज़ AWS में सॉल्यूशन आर्किटेक्ट हैं। वह जेनरेटिव एआई, एआई/एमएल और डेटा एनालिटिक्स पर ध्यान केंद्रित करता है। AWS में, आर्मंडो ग्राहकों को अपने सिस्टम में अत्याधुनिक जेनरेटिव AI क्षमताओं को एकीकृत करने, नवाचार और प्रतिस्पर्धी लाभ को बढ़ावा देने में मदद करता है। जब वह काम पर नहीं होता है, तो वह अपनी पत्नी और परिवार के साथ समय बिताना, लंबी पैदल यात्रा करना और दुनिया भर की यात्रा करना पसंद करता है।

स्पॉट_आईएमजी

नवीनतम खुफिया

स्पॉट_आईएमजी

हमारे साथ चैट करें

नमस्ते! मैं आपकी कैसे मदद कर सकता हूँ?