مدل های پایه Llama 2 از متا اکنون در Amazon SageMaker JumpStart | خدمات وب آمازون

مدل های پایه Llama 2 از متا اکنون در Amazon SageMaker JumpStart | خدمات وب آمازون

امروز، ما مشتاقیم اعلام کنیم که مدل های فونداسیون Llama 2 که توسط متا توسعه داده شده اند، از طریق آن برای مشتریان در دسترس هستند. Amazon SageMaker JumpStart. خانواده مدل‌های زبان بزرگ Llama 2 (LLMs) مجموعه‌ای از مدل‌های متنی تولیدی از پیش آموزش‌دیده و تنظیم‌شده است که در مقیاسی از ۷ میلیارد تا ۷۰ میلیارد پارامتر متغیر است. LLM های تنظیم شده به نام Llama-7-chat، برای موارد استفاده از گفتگو بهینه شده اند. می‌توانید به راحتی این مدل‌ها را امتحان کنید و با SageMaker JumpStart، که یک هاب یادگیری ماشین (ML) است که دسترسی به الگوریتم‌ها، مدل‌ها و راه‌حل‌های ML را فراهم می‌کند، استفاده کنید تا بتوانید به سرعت با ML شروع کنید.

در این پست نحوه استفاده از مدل های Llama 2 از طریق SageMaker JumpStart را توضیح می دهیم.

لاما 2 چیست؟

Llama 2 یک مدل زبان رگرسیون خودکار است که از معماری ترانسفورماتور بهینه شده استفاده می کند. Llama 2 برای استفاده تجاری و تحقیقاتی به زبان انگلیسی در نظر گرفته شده است. این در طیف وسیعی از اندازه‌های پارامتر - 7 میلیارد، 13 میلیارد و 70 میلیارد - و همچنین تغییرات از پیش آموزش‌دیده و تنظیم‌شده است. به گفته متا، نسخه‌های تنظیم‌شده از تنظیم دقیق نظارت شده (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) استفاده می‌کنند تا با ترجیحات انسان برای مفید بودن و ایمنی هماهنگ شوند. Llama 2 بر روی 2 تریلیون توکن داده از منابع در دسترس عموم از قبل آموزش داده شده بود. مدل‌های تنظیم‌شده برای چت دستیار در نظر گرفته شده‌اند، در حالی که مدل‌های از پیش آموزش‌دیده را می‌توان برای انواع وظایف تولید زبان طبیعی تطبیق داد. صرف نظر از اینکه توسعه‌دهنده از چه نسخه‌ای از مدل استفاده می‌کند، راهنمای استفاده مسئولانه از متا می تواند به هدایت تنظیمات دقیق اضافی که ممکن است برای سفارشی سازی و بهینه سازی مدل ها با کاهش ایمنی مناسب لازم باشد کمک کند.

SageMaker JumpStart چیست؟

با SageMaker JumpStart، پزشکان ML می‌توانند از میان مجموعه وسیعی از مدل‌های پایه منبع باز انتخاب کنند. پزشکان ML می توانند مدل های پایه را به صورت اختصاصی به کار گیرند آمازون SageMaker نمونه هایی از یک محیط جدا شده از شبکه و سفارشی کردن مدل ها با استفاده از SageMaker برای آموزش و استقرار مدل.

اکنون می‌توانید Llama 2 را با چند کلیک کشف و اجرا کنید Amazon SageMaker Studio یا به صورت برنامه نویسی از طریق SageMaker Python SDK، به شما امکان می دهد عملکرد مدل و کنترل های MLOps را با ویژگی های SageMaker مانند خطوط لوله آمازون SageMaker, دیباگر Amazon SageMaker، یا سیاهههای مربوط به کانتینر. این مدل در یک محیط امن AWS و تحت کنترل های VPC شما مستقر شده است و به اطمینان از امنیت داده ها کمک می کند. مدل‌های Llama 2 امروز در Amazon SageMaker Studio، در ابتدا در دسترس هستند us-east 1 و us-west 2 مناطق.

مدل ها را کشف کنید

می توانید از طریق SageMaker JumpStart در SageMaker Studio UI و SageMaker Python SDK به مدل های پایه دسترسی داشته باشید. در این بخش به نحوه کشف مدل ها در SageMaker Studio می پردازیم.

SageMaker Studio یک محیط توسعه یکپارچه (IDE) است که یک رابط بصری مبتنی بر وب را فراهم می کند که در آن می توانید به ابزارهای ساخته شده برای انجام تمام مراحل توسعه ML، از آماده سازی داده ها تا ساخت، آموزش، و استقرار مدل های ML خود دسترسی داشته باشید. برای جزئیات بیشتر در مورد نحوه شروع و راه اندازی SageMaker Studio، مراجعه کنید Amazon SageMaker Studio.

هنگامی که در استودیوی SageMaker هستید، می توانید به SageMaker JumpStart که شامل مدل های از پیش آموزش دیده، نوت بوک ها و راه حل های از پیش ساخته شده است، دسترسی پیدا کنید. راه حل های از پیش ساخته شده و خودکار.

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.

از صفحه فرود SageMaker JumpStart، می توانید راه حل ها، مدل ها، نوت بوک ها و منابع دیگر را جستجو کنید. شما می توانید دو مدل پرچمدار Llama 2 را در آن بیابید مدل های پایه: تولید متن چرخ فلک. اگر مدل‌های Llama 2 را نمی‌بینید، نسخه SageMaker Studio خود را با خاموش کردن و راه‌اندازی مجدد به‌روزرسانی کنید. برای اطلاعات بیشتر در مورد به روز رسانی نسخه، مراجعه کنید برنامه های استودیو را خاموش و به روز کنید.

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.

همچنین می توانید با انتخاب چهار مدل دیگر را بیابید تمام مدل های تولید متن را کاوش کنید یا جستجو برای llama در جعبه جستجو

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.

می‌توانید کارت مدل را برای مشاهده جزئیات مدل مانند مجوز، داده‌های مورد استفاده برای آموزش و نحوه استفاده انتخاب کنید. همچنین می توانید دو دکمه را پیدا کنید، گسترش و نوت بوک را باز کنید، که به شما در استفاده از مدل کمک می کند.

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.

وقتی یکی از دکمه‌ها را انتخاب می‌کنید، یک پنجره بازشو توافقنامه مجوز کاربر نهایی و خط‌مشی استفاده قابل قبول را برای تأیید شما نشان می‌دهد.

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.

پس از تایید، برای استفاده از مدل به مرحله بعدی خواهید رفت.

یک مدل مستقر کنید

وقتی انتخاب کردید گسترش و شرایط را بپذیرید، استقرار مدل آغاز خواهد شد. همچنین، می‌توانید از طریق دفترچه یادداشتی که با انتخاب نشان داده می‌شود، استفاده کنید نوت بوک را باز کنید. دفترچه یادداشت نمونه راهنمایی سرتاسری در مورد نحوه استقرار مدل برای استنتاج و پاکسازی منابع ارائه می دهد.

برای استقرار با استفاده از یک نوت بوک، با انتخاب یک مدل مناسب شروع می کنیم، مشخص شده توسط model_id. می توانید هر یک از مدل های انتخاب شده را با کد زیر در SageMaker مستقر کنید:

from sagemaker.jumpstart.model import JumpStartModel
my_model = JumpStartModel(model_id = "meta-textgeneration-llama-2-70b-f")
predictor = my_model.deploy()

این مدل را در SageMaker با تنظیمات پیش‌فرض، از جمله نوع نمونه پیش‌فرض و تنظیمات پیش‌فرض VPC، مستقر می‌کند. شما می توانید این تنظیمات را با تعیین مقادیر غیر پیش فرض در آن تغییر دهید JumpStartModel. پس از استقرار، می توانید استنتاج را در برابر نقطه پایانی مستقر شده از طریق پیش بینی SageMaker اجرا کنید:

payload = { “inputs”: [ [ {"role": "system", "content": "Always answer with Haiku"}, {"role": "user", "content": "I am going to Paris, what should I see?"}, ] ], "parameters":{"max_new_tokens":256, "top_p":0.9, "temperature":0.6}
}

مدل‌های چت با تنظیم دقیق (Llama-2-7b-chat، Llama-2-13b-chat، Llama-2-70b-chat) سابقه چت بین کاربر و دستیار چت را می‌پذیرند و گپ بعدی را ایجاد می‌کنند. مدل‌های از پیش آموزش‌دیده شده (Llama-2-7b، Llama-2-13b، Llama-2-70b) به یک اعلان رشته نیاز دارند و تکمیل متن را در اعلان ارائه شده انجام می‌دهند. کد زیر را ببینید:

predictor.predict(payload, custom_attributes="accept_eula=true")

توجه داشته باشید که به طور پیش فرض، accept_eula روی false تنظیم شده است. باید تنظیم کنید accept_eula=true برای فراخوانی موفقیت آمیز نقطه پایانی با انجام این کار، موافقت نامه مجوز کاربر و خط مشی استفاده قابل قبول را همانطور که قبلا ذکر شد می پذیرید. شما همچنین می توانید دانلود قرارداد مجوز

Custom_attributes برای عبور EULA جفت های کلید/مقدار استفاده می شود. کلید و مقدار با جدا شده اند = و جفت ها توسط جدا می شوند ;. اگر کاربر یک کلید را بیش از یک بار ارسال کند، آخرین مقدار نگه داشته شده و به کنترل کننده اسکریپت ارسال می شود (یعنی در این مورد برای منطق شرطی استفاده می شود). به عنوان مثال، اگر accept_eula=false; accept_eula=true سپس به سرور ارسال می شود  accept_eula=true نگه داشته می شود و به کنترل کننده اسکریپت منتقل می شود.

پارامترهای استنتاج فرآیند تولید متن را در نقطه پایانی کنترل می کنند. حداکثر کنترل توکن های جدید به اندازه خروجی تولید شده توسط مدل اشاره دارد. توجه داشته باشید که این عدد با تعداد کلمات یکسان نیست زیرا واژگان مدل با واژگان زبان انگلیسی یکسان نیست و هر نشانه ممکن است یک کلمه زبان انگلیسی نباشد. دما تصادفی بودن خروجی را کنترل می کند. دمای بالاتر منجر به خروجی‌های خلاقانه‌تر و توهم‌آمیزتر می‌شود. تمام پارامترهای استنتاج اختیاری هستند.

جدول زیر تمام مدل‌های Llama موجود در SageMaker JumpStart را به همراه مدل‌های Llama فهرست می‌کند model_ids، انواع نمونه های پیش فرض و حداکثر تعداد توکن های کل (مجموع تعداد نشانه های ورودی و تعداد توکن های تولید شده) پشتیبانی شده برای هر یک از این مدل ها.

نام مدل شناسه مدل حداکثر توکن ها نوع نمونه پیش فرض
لاما-2-7b meta-textgeneration-llama-2-7b 4096 ml.g5.2xlarge
Llama-2-7b-chat meta-textgeneration-llama-2-7b-f 4096 ml.g5.2xlarge
لاما-2-13b meta-textgeneration-llama-2-13b 4096 ml.g5.12xlarge
Llama-2-13b-chat meta-textgeneration-llama-2-13b-f 4096 ml.g5.12xlarge
لاما-2-70b meta-textgeneration-llama-2-70b 4096 ml.g5.48xlarge
Llama-2-70b-chat meta-textgeneration-llama-2-70b-f 4096 ml.g5.48xlarge

توجه داشته باشید که نقاط پایانی SageMaker دارای محدودیت زمانی 60 ثانیه هستند. بنابراین، حتی اگر مدل بتواند 4096 توکن تولید کند، اگر تولید متن بیش از 60 ثانیه طول بکشد، درخواست با شکست مواجه خواهد شد. برای مدل‌های 7B، 13B و 70B، توصیه می‌کنیم تنظیم کنید max_new_tokens به ترتیب از 1500، 1000 و 500 بیشتر نباشد، در حالی که تعداد کل توکن ها کمتر از 4K باشد.

استنباط و دستورهای مثال برای Llama-2-70b

می توانید از مدل های Llama برای تکمیل متن برای هر قطعه متنی استفاده کنید. از طریق تولید متن، می توانید وظایف مختلفی مانند پاسخ به سؤالات، ترجمه زبان، تجزیه و تحلیل احساسات و بسیاری موارد دیگر را انجام دهید. بار ورودی به نقطه پایانی شبیه کد زیر است:

payload = { “inputs”: str, (optional)"parameters":{"max_new_tokens":int, "top_p":float, "temperature":float}
}

در زیر چند نمونه از دستورات و متن تولید شده توسط مدل آمده است. تمام خروجی ها با پارامترهای استنتاج تولید می شوند {"max_new_tokens":256, "top_p":0.9, "temperature":0.6}.

Input: Simply put, the theory of relativity states that Output: 1) the laws of physics are the same for all observers in uniform motion relative to one another, and 2) the speed of light is the same for all observers, regardless of their relative motion or of the motion of the source of the light.
In the late 1800s, scientists believed that light travelled through a medium they called the luminiferous ether. But in 1887, Albert Michelson and Edward Morley designed an experiment to measure the speed of light in the ether, and found that the speed of light was the same no matter how they oriented their equipment. This result seemed to contradict the idea of the ether, and Michelson and Morley’s experiment became one of the most famous failed experiments in history.
In 1905, Albert Einstein published a paper that used the results of the Michelson-Morley experiment to develop the theory of special relativity. In 1915, Einstein published a paper on general relativity, which is a theory of gravitation.
In physics, the speed of light is considered to be a constant, and its value is 299,792,458 metres Input: I believe the meaning of life is Output: to be happy, to find joy in life, to love and be loved. To have the courage to be yourself and to be kind to others. To be able to express yourself, to create and to be inspired. To be able to give and receive. To be able to learn and grow. To be able to find beauty in the world and to be able to appreciate it. To be able to find peace and contentment. To be able to find meaning and purpose. To be able to make a difference in the world. To be able to find joy in the simple things. To be able to find joy in the difficult things. To be able to find joy in the journey. To be able to find joy in the destination. To be able to find joy in the present moment. To be able to find joy in the future. To be able to find joy in the past. To be able to find joy in the present. To be able to find joy in the future. To be able to find joy in the past. To be able to find joy in the present. To be able to find joy in the future. To be able to find joy in the past. To be able to find joy in the present. To be able to find joy Input: A brief message congratulating the team on the launch: Hi everyone, I just Output: wanted to send a quick note to congratulate everyone on the launch of our new website. I know it’s been a long time coming and I’m sure we’re all relieved that it’s finally out there. Thanks to everyone for their hard work and dedication over the last few months. I know it wasn’t always easy, but I think we can all be proud of the final product. I’m looking forward to seeing how our users respond to the new site and I’m confident that it will be a success. Thanks again, and enjoy the rest of your day! Best, [Your Name] [Your Title] [Your Company] [Your Email] [Your Phone Number] [Your Website] [Your Social Media Handles] [Your Address] [Your City, State, Zip Code] [Your Country] [Your Postal Code] [Your Website] [

در مثال بعدی، نحوه استفاده از مدل‌های Llama را با یادگیری درون متنی چند شات نشان می‌دهیم، جایی که نمونه‌های آموزشی در دسترس مدل را ارائه می‌کنیم. توجه داشته باشید که ما فقط روی مدل مستقر شده استنباط می کنیم و در طول این فرآیند وزن مدل تغییر نمی کند.

Input: Translate English to French: sea otter => loutre de mer peppermint => menthe poivrée plush girafe => girafe peluche cheese => Output: fromage chocolate => chocolat car => voiture hamster => hamster beer => bière bicycle => bicyclette banana => banane strawberry => fraise pizza => pizza cheeseburger => cheeseburger pineapple => ananas carrot => carotte watermelon => pastèque whale => baleine eggplant => aubergine cat => chat penguin => manchot lion => lion elephant => éléphant panda => panda tiger => tigre salmon => saumon squirrel => écureuil kangaroo => kangourou turtle => tortue octopus => poulpe frog => grenouille pig => cochon goldfish => poisson rouge tiger shark => requin tigre gorilla => gorille dol

استنباط و درخواست های مثال برای Llama-2-70b-chat

با مدل‌های Llama-2-Chat، که برای موارد استفاده از گفتگو بهینه شده‌اند، ورودی به نقاط پایانی مدل چت، سابقه قبلی بین دستیار چت و کاربر است. شما می توانید سوالاتی را در زمینه مکالمه ای که تاکنون اتفاق افتاده است بپرسید. همچنین می‌توانید پیکربندی سیستم را ارائه دهید، مانند شخصیت‌هایی که رفتار دستیار چت را تعریف می‌کنند. بار ورودی به نقطه پایانی شبیه کد زیر است:

payload = { “inputs”: [ [ (optional){"role": "system", "content": str}, (repeated k times) {"role": "user", "content": str}, {"role": "assistant", "content": str}, {"role": "user", "content": str}, ] ], (optional)"parameters":{"max_new_tokens":int, "top_p":float, "temperature":float}
}

در زیر چند نمونه از دستورات و متن تولید شده توسط مدل آمده است. همه خروجی ها با پارامترهای استنتاج تولید می شوند {"max_new_tokens": 512, "top_p": 0.9, "temperature": 0.6}.

Input:
User: what is the recipe of mayonnaise? Output:
Assistant: Sure, I can help you with that! Mayonnaise is a thick, creamy condiment made from a mixture of egg yolks, oil, vinegar or lemon juice, and seasonings. Here's a basic recipe for homemade mayonnaise: Ingredients: * 2 egg yolks
* 1/2 cup (120 ml) neutral-tasting oil, such as canola or grapeseed
* 1 tablespoon (15 ml) vinegar or lemon juice
* 1/2 teaspoon salt
* 1/4 teaspoon black pepper Instructions: 1. In a medium-sized bowl, whisk together the egg yolks, salt, and black pepper until well combined.
2. Slowly pour the oil into the bowl while continuously whisking the mixture. It's important to add the oil very slowly, otherwise the mixture can break and you'll end up with a separated, curdled mess.
3. Continue whisking until the mixture thickens and emulsifies, which should take about 5-7 minutes. You'll know it's ready when the mixture has doubled in volume and has a thick, creamy consistency.
4. Add the vinegar or lemon juice and continue whisking for another minute or two, until the flavors are fully incorporated.
5. Taste the mayonnaise and adjust the seasoning as needed. You can add more salt, pepper, or acid if desired.
6. Cover the bowl with plastic wrap and refrigerate the mayonnaise for at least 30 minutes before serving. This will allow the flavors to meld together and the mayonnaise to thicken further. That's it! This recipe makes about 1 1/2 cups (360 ml) of mayonnaise, which should be enough for a small to medium-sized batch of sandwiches or salads. You can also customize the recipe by adding different flavorings, such as garlic, mustard, or herbs, to create a unique taste. Enjoy!

در مثال زیر، کاربر با دستیار در مورد مکان های گردشگری در پاریس گفتگو کرده است. در مرحله بعد، کاربر در مورد اولین گزینه توصیه شده توسط دستیار چت پرس و جو می کند.

Input:
User: I am going to Paris, what should I see?
Assistant: Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris: 1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.
2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.
3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows. These are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world.
User: What is so great about #1? Output:
Assistant: The Eiffel Tower is a world-renowned iconic landmark that symbolizes Paris and France. It was built for the World's Fair in 1889 and was initially intended to be a temporary structure, but it has become a permanent part of the Parisian skyline. Here are some reasons why the Eiffel Tower is so great: 1. Engineering marvel: The Eiffel Tower was a groundbreaking feat of engineering at the time of its construction. It stands at 324 meters (1,063 feet) tall and was the tallest structure in the world for over 40 years.
2. Iconic design: The Eiffel Tower's distinctive shape and design make it instantly recognizable. It has been the subject of countless works of art, photographs, and films, and has become a symbol of Paris and France.
3. Panoramic views: The Eiffel Tower offers breathtaking views of the city from its observation decks. Visitors can enjoy a 360-degree view of Paris, including famous landmarks such as the Seine River, the Arc de Triomphe, and the Montmartre neighborhood.
4. Historical significance: The Eiffel Tower has played a significant role in Paris's history, having been the site of numerous important events, including the famous "Battle of the Eiffel Tower" during World War II.
5. Cultural impact: The Eiffel Tower has had a significant impact on popular culture, inspiring countless works of art, literature, and music. It has also been the subject of numerous documentaries and films, including the classic movie "An American in Paris."
6. Romantic setting: The Eiffel Tower is known for its romantic atmosphere, making it a popular destination for couples and newlyweds. It has been the site of countless marriage proposals and has been featured in numerous romantic films and literature.
7. Accessibility: The Eiffel Tower is easily accessible by public transportation, making it a convenient destination for visitors. It is also wheelchair-friendly, with elevators and ramps providing access to all levels. Overall, the Eiffel Tower is a must-see destination for anyone visiting Paris, offering a unique and unforgettable experience that combines history, culture, engineering, and rom

در مثال های زیر، پیکربندی سیستم را تنظیم می کنیم:

Input:
System: Always answer with Haiku
User: I am going to Paris, what should I see? Output:
Assistant: Eiffel Tower high
Art in the Louvre Museum
River Seine flows Input:
System: Always answer with emojis
User: How to go from Beijing to NY? Output:
Assistant: Here are the emojis that represent the steps to go from Beijing to New York: 🇨🇳🛫🛬🇺🇸🗽🏙️🚕💨🛩️🛬🛫😴💤🛩️🛬🛫😍

پاک کردن

پس از اتمام اجرای نوت بوک، مطمئن شوید که همه منابع را حذف کرده اید تا همه منابعی که در این فرآیند ایجاد کرده اید حذف شده و صورتحساب شما متوقف شود:

predictor.delete_model()
predictor.delete_endpoint()

نتیجه

در این پست نحوه شروع کار با مدل های Llama 2 را در استودیو SageMaker به شما نشان دادیم. با این کار، شما به شش مدل فونداسیون Llama 2 که حاوی میلیاردها پارامتر هستند دسترسی دارید. از آنجایی که مدل های فونداسیون از قبل آموزش دیده اند، می توانند به کاهش هزینه های آموزش و زیرساخت نیز کمک کنند و سفارشی سازی را برای موارد استفاده شما امکان پذیر کنند. برای شروع کار با SageMaker JumpStart، از منابع زیر دیدن کنید:


درباره نویسندگان

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.ژوئن برد یک مدیر محصول با SageMaker JumpStart است. او بر روی ساخت مدل های پایه به راحتی قابل کشف و استفاده برای کمک به مشتریان در ساخت برنامه های کاربردی هوش مصنوعی تمرکز دارد. تجربه او در آمازون همچنین شامل اپلیکیشن خرید موبایلی و تحویل آخرین مایل است.

ویوک مدان دکتر ویوک مدان یک دانشمند کاربردی با تیم آمازون SageMaker JumpStart است. او دکترای خود را از دانشگاه ایلینویز در Urbana-Champaign گرفت و پژوهشگر پست دکترا در جورجیا تک بود. او یک محقق فعال در یادگیری ماشین و طراحی الگوریتم است و مقالاتی در کنفرانس های EMNLP، ICLR، COLT، FOCS و SODA منتشر کرده است. Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai. دکتر کایل اولریش یک دانشمند کاربردی با تیم آمازون SageMaker JumpStart است. علایق تحقیقاتی او شامل الگوریتم های یادگیری ماشین مقیاس پذیر، بینایی کامپیوتر، سری های زمانی، ناپارامتریک های بیزی و فرآیندهای گاوسی است. دکترای او از دانشگاه دوک است و مقالاتی در NeurIPS، Cell و Neuron منتشر کرده است. Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai. دکتر آشیش ختان یک دانشمند ارشد کاربردی با Amazon SageMaker JumpStart است و به توسعه الگوریتم های یادگیری ماشین کمک می کند. او دکترای خود را از دانشگاه ایلینویز Urbana-Champaign گرفت. او یک محقق فعال در یادگیری ماشین و استنتاج آماری است و مقالات زیادی در کنفرانس های NeurIPS، ICML، ICLR، JMLR، ACL و EMNLP منتشر کرده است. Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai. ساندار رانگاناتان رئیس جهانی متخصصان GenAI/Frameworks GTM در AWS است. او بر توسعه استراتژی GTM برای مدل‌های زبان بزرگ، GenAI و بارهای کاری ML در مقیاس بزرگ در سرویس‌های AWS مانند Amazon EC2، EKS، EFA، AWS Batch و Amazon SageMaker تمرکز می‌کند. تجربه او شامل نقش های رهبری در مدیریت محصول و توسعه محصول در NetApp، Micron Technology، Qualcomm و Mentor Graphics است.

تمبر زمان:

بیشتر از آموزش ماشین AWS