이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart | 아마존 웹 서비스

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart | 아마존 웹 서비스

오늘 Meta에서 개발한 Llama 2 기초 모델을 통해 고객이 사용할 수 있음을 발표하게 되어 기쁩니다. Amazon SageMaker 점프스타트. 대규모 언어 모델(LLM)의 Llama 2 제품군은 7억에서 70억 매개변수 규모의 사전 훈련되고 미세 조정된 생성 텍스트 모델 모음입니다. Llama-2-chat이라고 하는 미세 조정된 LLM은 대화 사용 사례에 최적화되어 있습니다. 이러한 모델을 쉽게 시험해보고 ML을 빠르게 시작할 수 있도록 알고리즘, 모델 및 ML 솔루션에 대한 액세스를 제공하는 기계 학습(ML) 허브인 SageMaker JumpStart와 함께 사용할 수 있습니다.

이 게시물에서는 SageMaker JumpStart를 통해 Llama 2 모델을 사용하는 방법을 살펴봅니다.

라마 2 란?

Llama 2는 최적화된 변환기 아키텍처를 사용하는 자동 회귀 언어 모델입니다. Llama 2는 영어로 된 상업용 및 연구용입니다. 7억, 13억, 70억 등의 다양한 매개변수 크기와 사전 훈련 및 미세 조정된 변형으로 제공됩니다. Meta에 따르면 조정된 버전은 지도 미세 조정(SFT) 및 인간 피드백을 통한 강화 학습(RLHF)을 사용하여 유용성과 안전성에 대한 인간의 선호도에 맞춥니다. Llama 2는 공개적으로 사용 가능한 소스에서 2조 개의 데이터 토큰으로 사전 훈련되었습니다. 조정된 모델은 비서와 같은 채팅을 위한 반면 사전 훈련된 모델은 다양한 자연어 생성 작업에 맞게 조정할 수 있습니다. 개발자가 사용하는 모델의 버전에 관계없이 Meta의 책임감 있는 사용 가이드 적절한 안전 완화로 모델을 사용자 정의하고 최적화하는 데 필요할 수 있는 추가 미세 조정을 안내하는 데 도움을 줄 수 있습니다.

SageMaker JumpStart란?

SageMaker JumpStart를 통해 ML 실무자는 다양한 오픈 소스 기반 모델 중에서 선택할 수 있습니다. ML 실무자는 기본 모델을 전용으로 배포할 수 있습니다. 아마존 세이지 메이커 네트워크 격리 환경에서 인스턴스를 생성하고 모델 교육 및 배포를 위해 SageMaker를 사용하여 모델을 사용자 지정합니다.

이제 몇 번의 클릭만으로 Llama 2를 검색하고 배포할 수 있습니다. 아마존 세이지 메이커 스튜디오 또는 SageMaker Python SDK를 통해 프로그래밍 방식으로 다음과 같은 SageMaker 기능으로 모델 성능 및 MLOps 컨트롤을 파생할 수 있습니다. Amazon SageMaker 파이프 라인, Amazon SageMaker 디버거, 또는 컨테이너 로그. 이 모델은 AWS 보안 환경과 VPC 제어에 배포되어 데이터 보안을 보장합니다. Llama 2 모델은 현재 Amazon SageMaker Studio에서 사용할 수 있습니다. us-east 1us-west 2 지역.

모델 살펴보기

SageMaker Studio UI 및 SageMaker Python SDK에서 SageMaker JumpStart를 통해 기초 모델에 액세스할 수 있습니다. 이 섹션에서는 SageMaker Studio에서 모델을 검색하는 방법을 살펴봅니다.

SageMaker Studio는 데이터 준비에서 ML 모델 구축, 교육 및 배포에 이르기까지 모든 ML 개발 단계를 수행하기 위해 특별히 제작된 도구에 액세스할 수 있는 단일 웹 기반 시각적 인터페이스를 제공하는 통합 개발 환경(IDE)입니다. SageMaker Studio 시작 및 설정 방법에 대한 자세한 내용은 다음을 참조하십시오. 아마존 세이지 메이커 스튜디오.

SageMaker Studio에 있으면 사전 훈련된 모델, 노트북 및 사전 구축된 솔루션이 포함된 SageMaker JumpStart에 액세스할 수 있습니다. 사전 구축 및 자동화된 솔루션.

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함.

SageMaker JumpStart 랜딩 페이지에서 솔루션, 모델, 노트북 및 기타 리소스를 찾아볼 수 있습니다. 에서 두 개의 주력 Llama 2 모델을 찾을 수 있습니다. 재단 모델: 텍스트 생성 회전 목마. Llama 2 모델이 표시되지 않으면 종료하고 다시 시작하여 SageMaker Studio 버전을 업데이트하십시오. 버전 업데이트에 대한 자세한 내용은 다음을 참조하십시오. Studio 앱 종료 및 업데이트.

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함.

선택하여 다른 네 가지 모델 변형을 찾을 수도 있습니다. 모든 텍스트 생성 모델 살펴보기 또는 검색 llama 검색 창에

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함.

모델 카드를 선택하여 라이선스, 훈련에 사용된 데이터, 사용 방법 등 모델에 대한 세부 정보를 볼 수 있습니다. 두 개의 버튼도 찾을 수 있습니다. 배포노트북 열기, 모델을 사용하는 데 도움이 됩니다.

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함.

버튼 중 하나를 선택하면 최종 사용자 라이선스 계약 및 허용되는 사용 정책이 표시되는 팝업이 표시됩니다.

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함.

동의하면 모델 사용을 위한 다음 단계로 진행됩니다.

모델 배포

당신이 선택할 때 배포 약관에 동의하면 모델 배포가 시작됩니다. 또는 다음을 선택하여 표시되는 예제 노트북을 통해 배포할 수 있습니다. 노트북 열기. 예제 노트북은 추론을 위해 모델을 배포하고 리소스를 정리하는 방법에 대한 종단 간 지침을 제공합니다.

노트북을 사용하여 배포하려면 다음으로 지정된 적절한 모델을 선택하는 것으로 시작합니다. model_id. 다음 코드를 사용하여 SageMaker에서 선택한 모델을 배포할 수 있습니다.

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

이렇게 하면 기본 인스턴스 유형 및 기본 VPC 구성을 포함한 기본 구성으로 SageMaker에 모델이 배포됩니다. 다음에서 기본값이 아닌 값을 지정하여 이러한 구성을 변경할 수 있습니다. JumpStart모델. 배포 후 SageMaker 예측자를 통해 배포된 엔드포인트에 대해 추론을 실행할 수 있습니다.

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}
}

미세 조정된 채팅 모델(Llama-2-7b-chat, Llama-2-13b-chat, Llama-2-70b-chat)은 사용자와 채팅 도우미 간의 채팅 기록을 수락하고 후속 채팅을 생성합니다. 사전 훈련된 모델(Llama-2-7b, Llama-2-13b, Llama-2-70b)에는 문자열 프롬프트가 필요하며 제공된 프롬프트에서 텍스트 완성을 수행합니다. 다음 코드를 참조하십시오.

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

기본적으로 accept_eula 거짓으로 설정됩니다. 당신은 설정해야합니다 accept_eula=true 끝점을 성공적으로 호출합니다. 그렇게 함으로써 귀하는 앞서 언급한 사용자 라이선스 계약 및 사용 제한 정책에 동의하게 됩니다. 당신은 또한 수 다운로드 라이센스 계약.

Custom_attributes EULA를 통과하는 데 사용되는 키/값 쌍입니다. 키와 값은 다음과 같이 구분됩니다. = 쌍은 다음과 같이 구분됩니다. ;. 사용자가 동일한 키를 두 번 이상 전달하면 마지막 값이 유지되고 스크립트 처리기로 전달됩니다(즉, 이 경우 조건 논리에 사용됨). 예를 들어, accept_eula=false; accept_eula=true 서버로 전달된 다음  accept_eula=true 유지되어 스크립트 핸들러로 전달됩니다.

추론 매개변수는 끝점에서 텍스트 생성 프로세스를 제어합니다. 최대 새 토큰 제어는 모델에서 생성된 출력의 크기를 나타냅니다. 이는 모델의 어휘가 영어 어휘와 동일하지 않고 각 토큰이 영어 단어가 아닐 수 있기 때문에 단어 수와 같지 않음에 유의하십시오. 온도는 출력의 임의성을 제어합니다. 더 높은 온도는 더 창의적이고 환각적인 결과를 낳습니다. 모든 추론 매개변수는 선택 사항입니다.

다음 표에는 SageMaker JumpStart에서 사용할 수 있는 모든 Llama 모델과 model_ids, 기본 인스턴스 유형 및 이러한 각 모델에 대해 지원되는 최대 총 토큰 수(입력 토큰 수와 생성된 토큰 수의 합계).

모델 이름 모델 ID 최대 총 토큰 기본 인스턴스 유형
라마-2-7b 메타 텍스트 생성 라마-2-7b 4096 ml.g5.2xlarge
라마-2-7b-채팅 메타-텍스트세대-라마-2-7b-f 4096 ml.g5.2xlarge
라마-2-13b 메타 텍스트 생성 라마-2-13b 4096 ml.g5.12xlarge
라마-2-13b-채팅 메타-텍스트세대-라마-2-13b-f 4096 ml.g5.12xlarge
라마-2-70b 메타 텍스트 생성 라마-2-70b 4096 ml.g5.48xlarge
라마-2-70b-채팅 메타-텍스트세대-라마-2-70b-f 4096 ml.g5.48xlarge

SageMaker 엔드포인트의 제한 시간은 60초입니다. 따라서 모델이 4096개의 토큰을 생성할 수 있더라도 텍스트 생성에 60초 이상이 소요되면 요청이 실패합니다. 7B, 13B 및 70B 모델의 경우 다음을 설정하는 것이 좋습니다. max_new_tokens 총 토큰 수를 1500K 미만으로 유지하면서 각각 1000, 500 및 4보다 크지 않습니다.

Llama-2-70b에 대한 추론 및 예제 프롬프트

모든 텍스트에 대한 텍스트 완성을 위해 Llama 모델을 사용할 수 있습니다. 텍스트 생성을 통해 질문에 답하기, 언어 번역, 감정 분석 등과 같은 다양한 작업을 수행할 수 있습니다. 엔드포인트에 대한 입력 페이로드는 다음 코드와 같습니다.

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

다음은 몇 가지 샘플 예제 프롬프트와 모델에서 생성된 텍스트입니다. 모든 출력은 추론 매개변수로 생성됩니다. {"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] [

다음 예에서는 모델에 사용할 수 있는 교육 샘플을 제공하는 상황 내 학습과 함께 라마 모델을 사용하는 방법을 보여줍니다. 배포된 모델에 대해서만 추론하고 이 프로세스 중에 모델 가중치는 변경되지 않습니다.

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

Llama-2-70b-chat에 대한 추론 및 예제 프롬프트

대화 사용 사례에 최적화된 Llama-2-Chat 모델의 경우 채팅 모델 엔드포인트에 대한 입력은 채팅 도우미와 사용자 간의 이전 기록입니다. 지금까지 진행된 대화와 관련하여 상황에 맞는 질문을 할 수 있습니다. 채팅 도우미의 동작을 정의하는 페르소나와 같은 시스템 구성을 제공할 수도 있습니다. 엔드포인트에 대한 입력 페이로드는 다음 코드와 같습니다.

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}
}

다음은 몇 가지 샘플 예제 프롬프트와 모델에서 생성된 텍스트입니다. 모든 출력은 추론 매개변수로 생성됩니다. {"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!

다음 예에서 사용자는 파리의 관광지에 대해 어시스턴트와 대화를 나눴습니다. 다음으로 사용자는 채팅 도우미가 추천하는 첫 번째 옵션에 대해 문의합니다.

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

다음 예에서는 시스템 구성을 설정합니다.

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: 🇨🇳🛫🛬🇺🇸🗽🏙️🚕💨🛩️🛬🛫😴💤🛩️🛬🛫😍

정리

노트북 실행을 완료한 후 프로세스에서 생성한 모든 리소스가 삭제되고 청구가 중지되도록 모든 리소스를 삭제해야 합니다.

predictor.delete_model()
predictor.delete_endpoint()

결론

이 게시물에서는 SageMaker Studio에서 Llama 2 모델을 시작하는 방법을 설명했습니다. 이를 통해 수십억 개의 매개변수가 포함된 2개의 Llama XNUMX 기초 모델에 액세스할 수 있습니다. 기본 모델은 사전 교육을 받았기 때문에 교육 및 인프라 비용을 낮추고 사용 사례에 맞게 사용자 지정할 수 있습니다. SageMaker JumpStart를 시작하려면 다음 리소스를 방문하십시오.


저자 소개

이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함.준원 SageMaker JumpStart의 제품 관리자입니다. 그는 고객이 제너레이티브 AI 애플리케이션을 구축하는 데 도움이 되도록 기반 모델을 쉽게 검색하고 사용할 수 있도록 만드는 데 중점을 둡니다. Amazon에서의 그의 경험에는 모바일 쇼핑 애플리케이션 및 라스트 마일 배송도 포함됩니다.

비벡 마단 비벡 마단 박사 Amazon SageMaker JumpStart 팀의 응용 과학자입니다. 그는 일리노이 대학교 어바나 샴페인에서 박사 학위를 받았고 조지아 공대에서 박사후 연구원이었습니다. 그는 기계 학습 및 알고리즘 설계 분야에서 활발한 연구원이며 EMNLP, ICLR, COLT, FOCS 및 SODA 컨퍼런스에 논문을 발표했습니다. 이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함. 카일 울리히 박사 Amazon SageMaker JumpStart 팀의 응용 과학자입니다. 그의 연구 관심사는 확장 가능한 기계 학습 알고리즘, 컴퓨터 비전, 시계열, 베이지안 비모수 및 가우시안 프로세스를 포함합니다. Duke University에서 박사 학위를 받았으며 NeurIPS, Cell 및 Neuron에 논문을 발표했습니다. 이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함. Ashish Khetan 박사 Amazon SageMaker JumpStart의 수석 응용 과학자이며 기계 학습 알고리즘 개발을 돕습니다. 그는 University of Illinois Urbana-Champaign에서 박사 학위를 받았습니다. 그는 기계 학습 및 통계적 추론 분야에서 활동적인 연구원이며 NeurIPS, ICML, ICLR, JMLR, ACL 및 EMNLP 컨퍼런스에서 많은 논문을 발표했습니다. 이제 Meta의 Llama 2 기반 모델을 Amazon SageMaker JumpStart에서 사용할 수 있습니다 | Amazon Web Services PlatoBlockchain 데이터 인텔리전스. 수직 검색. 일체 포함. 순다르 랑가나단 AWS의 GenAI/Frameworks GTM 전문가 글로벌 책임자입니다. 그는 Amazon EC2, EKS, EFA, AWS Batch 및 Amazon SageMaker와 같은 AWS 서비스에서 대규모 언어 모델, GenAI 및 대규모 ML 워크로드를 위한 GTM 전략 개발에 주력하고 있습니다. 그의 경험에는 NetApp, Micron Technology, Qualcomm 및 Mentor Graphics에서 제품 관리 및 제품 개발의 리더십 역할이 포함됩니다.

타임 스탬프 :

더보기 AWS 기계 학습