نماذج مؤسسة Llama 2 من Meta متاحة الآن في Amazon SageMaker JumpStart | خدمات أمازون ويب

نماذج مؤسسة Llama 2 من Meta متاحة الآن في Amazon SageMaker JumpStart | خدمات أمازون ويب

اليوم ، يسعدنا أن نعلن أن نماذج الأساس Llama 2 التي طورتها Meta متاحة للعملاء من خلال أمازون سيج ميكر جومب ستارت. عائلة Llama 2 من نماذج اللغات الكبيرة (LLMs) عبارة عن مجموعة من نماذج نصية مُدرَّبة مسبقًا ومُحسَّنة بدقة تتراوح من 7 مليار إلى 70 مليار معلمة. تم تحسين LLMs ، التي تسمى Llama-2-chat ، لحالات استخدام الحوار. يمكنك تجربة هذه النماذج بسهولة واستخدامها مع SageMaker JumpStart ، وهو مركز للتعلم الآلي (ML) يوفر الوصول إلى الخوارزميات والنماذج وحلول التعلم الآلي حتى تتمكن من البدء بسرعة مع ML.

في هذا المنشور ، نتعرف على كيفية استخدام نماذج Llama 2 عبر SageMaker JumpStart.

ما هو اللاما 2

Llama 2 هو نموذج لغة ارتداد تلقائي يستخدم بنية محولات محسّنة. اللاما 2 مخصص للاستخدام التجاري والبحثي باللغة الإنجليزية. تأتي في مجموعة من أحجام المعلمات —7 مليار ، و 13 مليارًا ، و 70 مليارًا - بالإضافة إلى الاختلافات المُدربة مسبقًا والمُحكمة. وفقًا لـ Meta ، تستخدم الإصدارات المضبوطة الضبط الدقيق الخاضع للإشراف (SFT) والتعلم المعزز من خلال التغذية المرتدة البشرية (RLHF) للتوافق مع تفضيلات الإنسان من أجل المساعدة والسلامة. تم تدريب Llama 2 مسبقًا على 2 تريليون رمز من البيانات من المصادر المتاحة للجمهور. النماذج المضبوطة مخصصة للدردشة المشابهة للمساعد ، في حين يمكن تكييف النماذج المدربة مسبقًا لمجموعة متنوعة من مهام إنشاء اللغة الطبيعية. بغض النظر عن إصدار النموذج الذي يستخدمه المطور ، فإن ملف دليل الاستخدام المسؤول من Meta يمكن أن تساعد في توجيه الضبط الدقيق الإضافي الذي قد يكون ضروريًا لتخصيص النماذج وتحسينها باستخدام وسائل تخفيف السلامة المناسبة.

ما هو برنامج SageMaker JumpStart

مع SageMaker JumpStart ، يمكن لممارسي تعلم الآلة الاختيار من بين مجموعة واسعة من نماذج الأساس مفتوحة المصدر. يمكن لممارسي تعلم الآلة نشر نماذج مؤسسة مخصصة الأمازون SageMaker مثيلات من بيئة شبكة معزولة وتخصيص النماذج باستخدام SageMaker للتدريب على النموذج ونشره.

يمكنك الآن اكتشاف ونشر Llama 2 ببضع نقرات في أمازون ساجميكر ستوديو أو برمجيًا من خلال SageMaker Python SDK ، مما يتيح لك اشتقاق أداء النموذج وعناصر تحكم MLOps باستخدام ميزات SageMaker مثل خطوط أنابيب Amazon SageMaker, الأمازون SageMaker المصحح، أو سجلات الحاوية. يتم نشر النموذج في بيئة آمنة AWS وتحت ضوابط VPC الخاصة بك ، مما يساعد على ضمان أمان البيانات. تتوفر طرازات Llama 2 اليوم في Amazon SageMaker Studio ، مبدئيًا بتنسيق us-east 1 و us-west 2 المناطق.

اكتشف الموديلات

يمكنك الوصول إلى نماذج الأساس من خلال SageMaker JumpStart في SageMaker Studio UI و SageMaker Python SDK. في هذا القسم ، ننتقل إلى كيفية اكتشاف النماذج في SageMaker Studio.

SageMaker Studio عبارة عن بيئة تطوير متكاملة (IDE) توفر واجهة مرئية واحدة قائمة على الويب حيث يمكنك الوصول إلى الأدوات المصممة لغرض تنفيذ جميع خطوات تطوير ML ، من إعداد البيانات إلى البناء والتدريب ونشر نماذج ML الخاصة بك. لمزيد من التفاصيل حول كيفية البدء وإعداد SageMaker Studio ، يرجى الرجوع إلى أمازون ساجميكر ستوديو.

بمجرد دخولك إلى SageMaker Studio ، يمكنك الوصول إلى SageMaker JumpStart ، الذي يحتوي على نماذج مدربة مسبقًا ، وأجهزة كمبيوتر محمولة ، وحلول تم إنشاؤها مسبقًا ، ضمن حلول آلية ومبنية مسبقًا.

نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية.

من الصفحة المقصودة SageMaker JumpStart ، يمكنك التصفح بحثًا عن الحلول والنماذج وأجهزة الكمبيوتر المحمولة والموارد الأخرى. يمكنك العثور على طرازين رائدين من Llama 2 في نماذج التأسيس: توليد النص دائري. إذا كنت لا ترى طرازات Llama 2 ، فقم بتحديث إصدار SageMaker Studio الخاص بك عن طريق إيقاف التشغيل وإعادة التشغيل. لمزيد من المعلومات حول تحديثات الإصدار ، راجع قم بإيقاف تشغيل وتحديث تطبيقات الاستوديو.

نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية.

يمكنك أيضًا العثور على أربعة نماذج أخرى من خلال الاختيار استكشف جميع نماذج إنشاء النص أو البحث عن llama في مربع البحث.

نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية.

يمكنك اختيار بطاقة النموذج لعرض تفاصيل حول النموذج مثل الترخيص والبيانات المستخدمة للتدريب وكيفية الاستخدام. يمكنك أيضًا العثور على زرين ، نشر و افتح المفكرةالتي تساعدك على استخدام النموذج.

نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية.

عند اختيار أي من الزرين ، ستظهر نافذة منبثقة اتفاقية ترخيص المستخدم النهائي وسياسة الاستخدام المقبول لتقر بها.

نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية.

عند الإقرار ، ستنتقل إلى الخطوة التالية لاستخدام النموذج.

نشر نموذج

عندما تختار نشر والاعتراف بالشروط ، سيبدأ نشر النموذج. بدلاً من ذلك ، يمكنك النشر من خلال مثال دفتر الملاحظات الذي يظهر عن طريق الاختيار افتح المفكرة. يوفر نموذج دفتر الملاحظات إرشادات شاملة حول كيفية نشر النموذج لموارد الاستدلال والتنظيف.

للنشر باستخدام جهاز كمبيوتر محمول ، نبدأ باختيار نموذج مناسب ، محدد بواسطة model_id. يمكنك نشر أي من النماذج المحددة على SageMaker باستخدام الكود التالي:

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

يؤدي هذا إلى نشر النموذج على SageMaker مع التكوينات الافتراضية ، بما في ذلك نوع المثيل الافتراضي وتكوينات VPC الافتراضية. يمكنك تغيير هذه التكوينات عن طريق تحديد قيم غير افتراضية بتنسيق نموذج JumpStart. بعد نشره ، يمكنك تشغيل الاستدلال مقابل نقطة النهاية المنشورة من خلال توقع SageMaker:

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}
}

نماذج الدردشة الدقيقة (Llama-2-7b-chat ، Llama-2-13b-chat ، Llama-2-70b-chat) تقبل سجل الدردشة بين المستخدم ومساعد الدردشة ، وإنشاء الدردشة اللاحقة. تتطلب النماذج المدربة مسبقًا (Llama-2-7b ، Llama-2-13b ، Llama-2-70b) موجه سلسلة وإكمال النص في الموجه المقدم. انظر الكود التالي:

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

لاحظ أنه افتراضيًا ، accept_eula تم تعيينه على خطأ. تحتاج إلى ضبط accept_eula=true لاستدعاء نقطة النهاية بنجاح. من خلال القيام بذلك ، فإنك تقبل اتفاقية ترخيص المستخدم وسياسة الاستخدام المقبول كما هو مذكور سابقًا. بامكانك ايضا بإمكانك تحميله اتفاقية الترخيص.

Custom_attributes تستخدم لتمرير اتفاقية ترخيص المستخدم النهائي (EULA) هي أزواج مفتاح / قيمة. المفتاح والقيمة مفصولة بـ = والأزواج مفصولة بـ ;. إذا قام المستخدم بتمرير نفس المفتاح أكثر من مرة ، يتم الاحتفاظ بالقيمة الأخيرة وتمريرها إلى معالج البرنامج النصي (على سبيل المثال ، في هذه الحالة ، يتم استخدامه للمنطق الشرطي). على سبيل المثال ، إذا accept_eula=false; accept_eula=true يتم تمريره إلى الخادم ، ثم  accept_eula=true يتم الاحتفاظ بها وتمريرها إلى معالج البرنامج النصي.

تتحكم معلمات الاستدلال في عملية إنشاء النص عند نقطة النهاية. يشير الحد الأقصى للتحكم في الرموز المميزة الجديدة إلى حجم المخرجات التي تم إنشاؤها بواسطة النموذج. لاحظ أن هذا ليس هو نفسه عدد الكلمات لأن مفردات النموذج تختلف عن مفردات اللغة الإنجليزية ، وقد لا يكون كل رمز مميزًا كلمة باللغة الإنجليزية. تتحكم درجة الحرارة في العشوائية في الإخراج. ينتج عن ارتفاع درجة الحرارة نتائج أكثر إبداعًا وهلوسة. جميع معلمات الاستدلال اختيارية.

يسرد الجدول التالي جميع نماذج Llama المتوفرة في SageMaker JumpStart جنبًا إلى جنب مع ملف model_ids، وأنواع المثيلات الافتراضية ، والحد الأقصى لعدد الرموز (مجموع عدد الرموز المميزة للإدخال وعدد الرموز المميزة التي تم إنشاؤها) المدعومة لكل من هذه النماذج.

نموذج الاسم معرف النموذج ماكس إجمالي الرموز نوع المثيل الافتراضي
اللاما 2-7 ب جيل النص الفوقي-اللاما-2-7 ب 4096 ml.g5.2xlarge
Llama-2-7b- دردشة التلوي النص جيل اللاما 2-7b-f 4096 ml.g5.2xlarge
اللاما 2-13 ب جيل النص الفوقي-اللاما-2-13 ب 4096 ml.g5.12xlarge
Llama-2-13b- دردشة التلوي النص جيل اللاما 2-13b-f 4096 ml.g5.12xlarge
اللاما 2-70 ب جيل النص الفوقي-اللاما-2-70 ب 4096 ml.g5.48xlarge
Llama-2-70b- دردشة التلوي النص جيل اللاما 2-70b-f 4096 ml.g5.48xlarge

لاحظ أن نقاط نهاية SageMaker لها حد مهلة يبلغ 60 ثانية. وبالتالي ، على الرغم من أن النموذج قد يكون قادرًا على إنشاء 4096 رمزًا ، إذا استغرق إنشاء النص أكثر من 60 ثانية ، فسيفشل الطلب. بالنسبة للطرازات 7B ، و 13 B ، و 70 B ، نوصي بالتعيين max_new_tokens لا يزيد عن 1500 و 1000 و 500 على التوالي ، مع الاحتفاظ بإجمالي عدد الرموز المميزة أقل من 4K.

محفزات الاستدلال والأمثلة لـ Llama-2-70b

يمكنك استخدام نماذج اللاما لإكمال النص لأي جزء من النص. من خلال إنشاء النص ، يمكنك أداء مجموعة متنوعة من المهام ، مثل الإجابة على الأسئلة وترجمة اللغة وتحليل المشاعر وغير ذلك الكثير. تبدو الحمولة المدخلة إلى نقطة النهاية مثل الكود التالي:

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

فيما يلي بعض نماذج المطالبات والنص الذي تم إنشاؤه بواسطة النموذج. يتم إنشاء جميع المخرجات باستخدام معلمات الاستدلال {"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] [

في المثال التالي ، نعرض كيفية استخدام نماذج اللاما مع القليل من التعلم في السياق ، حيث نقدم عينات تدريبية متاحة للنموذج. لاحظ أننا نقوم فقط بالاستدلال على النموذج المنشور وأثناء هذه العملية ، لا تتغير أوزان النموذج.

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

مطالبات الاستدلال والأمثلة لـ Llama-2-70b-chat

مع نماذج Llama-2-Chat ، التي تم تحسينها لحالات استخدام الحوار ، يكون الإدخال إلى نقاط نهاية نموذج الدردشة هو السجل السابق بين مساعد الدردشة والمستخدم. يمكنك طرح أسئلة تتعلق بالمحادثة التي حدثت حتى الآن. يمكنك أيضًا توفير تكوين النظام ، مثل الشخصيات التي تحدد سلوك مساعد الدردشة. تبدو حمولة الإدخال إلى نقطة النهاية مثل الكود التالي:

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}
}

فيما يلي بعض نماذج المطالبات والنص الذي تم إنشاؤه بواسطة النموذج. يتم إنشاء جميع المخرجات باستخدام معلمات الاستدلال {"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!

في المثال التالي ، أجرى المستخدم محادثة مع المساعد حول المواقع السياحية في باريس. بعد ذلك ، يستفسر المستخدم عن الخيار الأول الذي أوصى به مساعد الدردشة.

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

في الأمثلة التالية ، قمنا بتعيين تكوين النظام:

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: 🇨🇳🛫🛬🇺🇸🗽🏙️🚕💨🛩️🛬🛫😴💤🛩️🛬🛫😍

تنظيف

بعد الانتهاء من تشغيل دفتر الملاحظات ، تأكد من حذف جميع الموارد بحيث يتم حذف جميع الموارد التي قمت بإنشائها في العملية وإيقاف الفواتير الخاصة بك:

predictor.delete_model()
predictor.delete_endpoint()

وفي الختام

في هذا المنشور ، أوضحنا لك كيفية البدء في استخدام طرازات Llama 2 في SageMaker Studio. باستخدام هذا ، يمكنك الوصول إلى ستة نماذج أساسية من Llama 2 تحتوي على مليارات من المعلمات. نظرًا لأن نماذج الأساس مدربة مسبقًا ، فيمكنها أيضًا المساعدة في خفض تكاليف التدريب والبنية التحتية وتمكين التخصيص لحالة الاستخدام الخاصة بك. لبدء استخدام SageMaker JumpStart ، قم بزيارة الموارد التالية:


عن المؤلفين

نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية.وون يونيو هو مدير منتج مع SageMaker JumpStart. يركز على جعل نماذج الأساس سهلة الاكتشاف والاستخدام لمساعدة العملاء على بناء تطبيقات الذكاء الاصطناعي التوليدية. تشمل تجربته في أمازون أيضًا تطبيق التسوق عبر الهاتف المحمول والتسليم في الميل الأخير.

فيفيك مادان الدكتور فيفيك مادان هو عالم تطبيقي مع فريق Amazon SageMaker JumpStart. حصل على الدكتوراه من جامعة إلينوي في Urbana-Champaign وكان باحثًا بعد الدكتوراه في Georgia Tech. وهو باحث نشط في التعلم الآلي وتصميم الخوارزمية وقد نشر أوراقًا علمية في مؤتمرات EMNLP و ICLR و COLT و FOCS و SODA. نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية. دكتور كايل أولريش هو عالم تطبيقي مع فريق Amazon SageMaker JumpStart. تشمل اهتماماته البحثية خوارزميات التعلم الآلي القابلة للتطوير ، والرؤية الحاسوبية ، والسلاسل الزمنية ، والمعاملات البايزية غير البارامترية ، والعمليات الغاوسية. حصل على درجة الدكتوراه من جامعة ديوك وقد نشر أبحاثًا في NeurIPS و Cell و Neuron. نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية. د. أشيش خيتان هو عالم تطبيقي أقدم في Amazon SageMaker JumpStart ويساعد في تطوير خوارزميات التعلم الآلي. حصل على الدكتوراه من جامعة إلينوي في أوربانا شامبين. وهو باحث نشط في التعلم الآلي والاستدلال الإحصائي ، وقد نشر العديد من الأوراق البحثية في مؤتمرات NeurIPS و ICML و ICLR و JMLR و ACL و EMNLP. نماذج Llama 2 الأساسية من Meta متاحة الآن في Amazon SageMaker JumpStart | أمازون ويب سيرفيسز PlatoBlockchain Data Intelligence. البحث العمودي. منظمة العفو الدولية. سوندار رانجاناثان هو الرئيس العالمي لأخصائيي GenAI / Frameworks GTM في AWS. يركز على تطوير إستراتيجية GTM لنماذج اللغات الكبيرة ، GenAI ، وأعباء عمل ML على نطاق واسع عبر خدمات AWS مثل Amazon EC2 و EKS و EFA و AWS Batch و Amazon SageMaker. تشمل خبرته الأدوار القيادية في إدارة المنتجات وتطوير المنتجات في NetApp و Micron Technology و Qualcomm و Mentor Graphics.

الطابع الزمني:

اكثر من التعلم الآلي من AWS