โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | บริการเว็บอเมซอน

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | บริการเว็บอเมซอน

วันนี้เรารู้สึกตื่นเต้นที่จะประกาศว่าโมเดลรองพื้น Llama 2 ที่พัฒนาโดย Meta พร้อมให้ลูกค้าใช้งานผ่าน Amazon SageMaker JumpStart. ตระกูล Llama 2 ของโมเดลภาษาขนาดใหญ่ (LLMs) คือชุดของโมเดลข้อความกำเนิดที่ผ่านการฝึกอบรมและปรับแต่งมาอย่างดี ซึ่งมีตั้งแต่ขนาด 7 พันล้านถึง 70 พันล้านพารามิเตอร์ LLM ที่ได้รับการปรับแต่งอย่างละเอียดเรียกว่า Llama-2-chat ได้รับการปรับให้เหมาะสมสำหรับกรณีการใช้งานบทสนทนา คุณสามารถลองใช้โมเดลเหล่านี้ได้อย่างง่ายดายและใช้กับ SageMaker JumpStart ซึ่งเป็นฮับการเรียนรู้ของเครื่อง (ML) ที่ให้การเข้าถึงอัลกอริทึม โมเดล และโซลูชัน ML เพื่อให้คุณสามารถเริ่มต้นใช้งาน ML ได้อย่างรวดเร็ว

ในโพสต์นี้ เราจะแนะนำวิธีใช้โมเดลลามะ 2 ผ่าน SageMaker JumpStart

ลามะ 2 คืออะไร

Llama 2 เป็นโมเดลภาษาถอยหลังอัตโนมัติที่ใช้สถาปัตยกรรมหม้อแปลงที่ปรับให้เหมาะสม Llama 2 มีไว้สำหรับใช้ในเชิงพาณิชย์และการวิจัยเป็นภาษาอังกฤษ มีขนาดพารามิเตอร์หลายขนาด ได้แก่ 7 พันล้าน 13 พันล้าน และ 70 พันล้าน ตลอดจนรูปแบบต่างๆ ที่ผ่านการฝึกอบรมและปรับแต่งอย่างละเอียด จากข้อมูลของ Meta เวอร์ชันที่ปรับแต่งจะใช้การปรับแบบละเอียดภายใต้การดูแล (SFT) และการเรียนรู้แบบเสริมแรงด้วยคำติชมของมนุษย์ (RLHF) เพื่อให้สอดคล้องกับความชอบของมนุษย์ในด้านความช่วยเหลือและความปลอดภัย Llama 2 ได้รับการฝึกอบรมล่วงหน้าโดยใช้ข้อมูล 2 ล้านล้านโทเค็นจากแหล่งข้อมูลสาธารณะ โมเดลที่ได้รับการปรับแต่งมีไว้สำหรับการแชทแบบผู้ช่วย ในขณะที่โมเดลที่ผ่านการฝึกอบรมล่วงหน้าสามารถปรับให้เหมาะกับงานสร้างภาษาธรรมชาติที่หลากหลาย ไม่ว่านักพัฒนาจะใช้โมเดลรุ่นใดก็ตาม คู่มือการใช้งานอย่างรับผิดชอบจาก Meta สามารถช่วยแนะนำการปรับละเอียดเพิ่มเติมที่อาจจำเป็นในการปรับแต่งและเพิ่มประสิทธิภาพโมเดลด้วยการบรรเทาความปลอดภัยที่เหมาะสม

SageMaker JumpStart คืออะไร

ด้วย SageMaker JumpStart ผู้ปฏิบัติงานด้าน ML สามารถเลือกโมเดลพื้นฐานของโอเพ่นซอร์สที่มีให้เลือกมากมาย ผู้ปฏิบัติงาน ML สามารถนำโมเดลพื้นฐานไปปรับใช้ได้ อเมซอน SageMaker อินสแตนซ์จากสภาพแวดล้อมแบบแยกเครือข่ายและปรับแต่งโมเดลโดยใช้ SageMaker สำหรับการฝึกโมเดลและการปรับใช้

ตอนนี้คุณสามารถค้นหาและใช้งาน Llama 2 ได้ด้วยการคลิกเพียงไม่กี่ครั้ง สตูดิโอ Amazon SageMaker หรือทางโปรแกรมผ่าน SageMaker Python SDK ทำให้คุณได้รับประสิทธิภาพของแบบจำลองและการควบคุม MLOps ด้วยคุณลักษณะของ SageMaker เช่น ท่อส่ง Amazon SageMaker, ดีบักเกอร์ Amazon SageMakerหรือบันทึกคอนเทนเนอร์ มีการปรับใช้โมเดลในสภาพแวดล้อมที่ปลอดภัยของ AWS และภายใต้การควบคุม VPC ของคุณ ซึ่งช่วยรับประกันความปลอดภัยของข้อมูล โมเดล Llama 2 มีวางจำหน่ายแล้ววันนี้ใน Amazon SageMaker Studio โดยเริ่มต้นใน us-east 1 และ us-west 2 ภูมิภาค

ค้นพบแบบจำลอง

คุณสามารถเข้าถึงโมเดลพื้นฐานผ่าน SageMaker JumpStart ใน SageMaker Studio UI และ SageMaker Python SDK ในส่วนนี้ เราจะพูดถึงวิธีค้นหาโมเดลใน SageMaker Studio

SageMaker Studio เป็นสภาพแวดล้อมการพัฒนาแบบผสานรวม (IDE) ที่มีอินเทอร์เฟซภาพบนเว็บเดียว ซึ่งคุณสามารถเข้าถึงเครื่องมือที่สร้างขึ้นตามวัตถุประสงค์เพื่อดำเนินการตามขั้นตอนการพัฒนา ML ทั้งหมด ตั้งแต่การเตรียมข้อมูลไปจนถึงการสร้าง การฝึกอบรม และนำโมเดล ML ของคุณไปใช้จริง สำหรับรายละเอียดเพิ่มเติมเกี่ยวกับวิธีเริ่มต้นใช้งานและตั้งค่า SageMaker Studio โปรดดูที่ สตูดิโอ Amazon SageMaker.

เมื่อคุณอยู่ใน SageMaker Studio แล้ว คุณสามารถเข้าถึง SageMaker JumpStart ซึ่งมีโมเดลที่ฝึกไว้ล่วงหน้า โน้ตบุ๊ก และโซลูชันที่สร้างไว้ล่วงหน้าภายใต้ โซลูชันที่สร้างไว้ล่วงหน้าและอัตโนมัติ.

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI.

จากหน้า Landing Page ของ SageMaker JumpStart คุณสามารถเรียกดูโซลูชัน รุ่น โน้ตบุ๊ก และแหล่งข้อมูลอื่นๆ คุณสามารถค้นหา Llama 2 รุ่นเรือธงทั้งสองรุ่นได้ใน โมเดลพื้นฐาน: การสร้างข้อความ ม้าหมุน หากคุณไม่เห็นโมเดล Llama 2 ให้อัปเดตเวอร์ชัน SageMaker Studio ของคุณโดยปิดเครื่องและรีสตาร์ท สำหรับข้อมูลเพิ่มเติมเกี่ยวกับการอัปเดตเวอร์ชัน โปรดดูที่ ปิดและอัปเดตแอป Studio.

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI.

คุณยังสามารถค้นหารูปแบบรุ่นอื่นๆ อีกสี่รุ่นได้โดยเลือก สำรวจโมเดลการสร้างข้อความทั้งหมด หรือค้นหา llama ในช่องค้นหา

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI.

คุณสามารถเลือกการ์ดรุ่นเพื่อดูรายละเอียดเกี่ยวกับรุ่น เช่น ใบอนุญาต ข้อมูลที่ใช้ในการฝึก และวิธีการใช้งาน คุณยังสามารถค้นหาปุ่มสองปุ่ม ปรับใช้ และ เปิดสมุดบันทึกซึ่งช่วยให้คุณใช้โมเดลได้

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI.

เมื่อคุณเลือกปุ่มใดปุ่มหนึ่ง ป๊อปอัปจะแสดงข้อตกลงสิทธิ์การใช้งานของผู้ใช้ปลายทางและนโยบายการใช้งานที่ยอมรับได้เพื่อให้คุณรับทราบ

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI.

เมื่อรับทราบ คุณจะไปยังขั้นตอนต่อไปเพื่อใช้โมเดล

ปรับใช้โมเดล

เมื่อคุณเลือก ปรับใช้ และรับทราบเงื่อนไข การปรับใช้แบบจำลองจะเริ่มขึ้น หรือคุณสามารถปรับใช้ผ่านสมุดบันทึกตัวอย่างที่แสดงขึ้นโดยเลือก เปิดสมุดบันทึก. สมุดบันทึกตัวอย่างให้คำแนะนำแบบ end-to-end เกี่ยวกับวิธีปรับใช้แบบจำลองสำหรับการอนุมานและล้างข้อมูลทรัพยากร

ในการปรับใช้โดยใช้โน้ตบุ๊ก เราเริ่มต้นด้วยการเลือกรุ่นที่เหมาะสมซึ่งระบุโดย model_id. คุณสามารถปรับใช้โมเดลที่เลือกใดๆ บน SageMaker ด้วยรหัสต่อไปนี้:

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

ซึ่งปรับใช้โมเดลบน SageMaker ด้วยการกำหนดค่าเริ่มต้น รวมถึงประเภทอินสแตนซ์เริ่มต้นและการกำหนดค่า VPC เริ่มต้น คุณสามารถเปลี่ยนการกำหนดค่าเหล่านี้ได้โดยการระบุค่าที่ไม่ใช่ค่าเริ่มต้นใน JumpStartโมเดล. หลังจากปรับใช้แล้ว คุณสามารถเรียกใช้การอนุมานเทียบกับจุดสิ้นสุดที่ปรับใช้ผ่านตัวทำนาย 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}
}

รูปแบบการแชทที่ปรับแต่งมาอย่างดี (Llama-2-7b-chat, Llama-2-13b-chat, Llama-2-70b-chat) ยอมรับประวัติการแชทระหว่างผู้ใช้และผู้ช่วยแชท และสร้างการแชทที่ตามมา โมเดลที่ผ่านการฝึกอบรมล่วงหน้า (Llama-2-7b, Llama-2-13b, Llama-2-70b) ต้องใช้ข้อความพร้อมต์และดำเนินการเติมข้อความในข้อความแจ้งที่ให้มา ดูรหัสต่อไปนี้:

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

โปรดทราบว่าโดยค่าเริ่มต้น accept_eula ถูกตั้งค่าเป็นเท็จ คุณต้องตั้งค่า accept_eula=true เพื่อเรียกใช้จุดสิ้นสุดได้สำเร็จ การดำเนินการดังกล่าวแสดงว่าคุณยอมรับข้อตกลงใบอนุญาตผู้ใช้และนโยบายการใช้งานที่ยอมรับได้ตามที่กล่าวไว้ก่อนหน้านี้ นอกจากนี้คุณยังสามารถ ดาวน์โหลด ข้อตกลงใบอนุญาต

Custom_attributes ใช้เพื่อผ่าน EULA คือคู่คีย์/ค่า คีย์และค่าจะถูกคั่นด้วย = และคู่ที่คั่นด้วย ;. ถ้าผู้ใช้ส่งคีย์เดียวกันมากกว่าหนึ่งครั้ง ค่าสุดท้ายจะถูกเก็บไว้และส่งผ่านไปยังตัวจัดการสคริปต์ (เช่น ในกรณีนี้ ใช้สำหรับตรรกะแบบมีเงื่อนไข) ตัวอย่างเช่น ถ้า accept_eula=false; accept_eula=true จะถูกส่งต่อไปยังเซิร์ฟเวอร์แล้ว  accept_eula=true ถูกเก็บไว้และส่งต่อไปยังตัวจัดการสคริปต์

พารามิเตอร์การอนุมานจะควบคุมกระบวนการสร้างข้อความที่จุดสิ้นสุด การควบคุมโทเค็นใหม่สูงสุดหมายถึงขนาดของเอาต์พุตที่สร้างโดยโมเดล โปรดทราบว่านี่ไม่เหมือนกับจำนวนคำ เนื่องจากคำศัพท์ของแบบจำลองนั้นไม่เหมือนกับคำศัพท์ภาษาอังกฤษ และแต่ละโทเค็นอาจไม่ใช่คำในภาษาอังกฤษ อุณหภูมิควบคุมความสุ่มในเอาต์พุต อุณหภูมิที่สูงขึ้นส่งผลให้เกิดผลงานที่สร้างสรรค์และหลอนประสาทมากขึ้น พารามิเตอร์การอนุมานทั้งหมดเป็นทางเลือก

ตารางต่อไปนี้แสดงโมเดลลามะทั้งหมดที่มีอยู่ใน SageMaker JumpStart พร้อมกับ model_idsประเภทอินสแตนซ์เริ่มต้น และจำนวนสูงสุดของโทเค็นทั้งหมด (ผลรวมของจำนวนโทเค็นอินพุตและจำนวนโทเค็นที่สร้างขึ้น) ที่รองรับสำหรับแต่ละโมเดลเหล่านี้

ชื่อรุ่น รหัสรุ่น โทเค็นทั้งหมดสูงสุด ประเภทอินสแตนซ์เริ่มต้น
ลามะ-2-7b เมตา-ข้อความรุ่น-llama-2-7b 4096 มล.g5.2xlarge
ลามะ-2-7b-แชท meta-textgeneration-ลามะ-2-7b-f 4096 มล.g5.2xlarge
ลามะ-2-13b เมตา-ข้อความรุ่น-llama-2-13b 4096 มล.g5.12xlarge
ลามะ-2-13b-แชท meta-textgeneration-ลามะ-2-13b-f 4096 มล.g5.12xlarge
ลามะ-2-70b เมตา-ข้อความรุ่น-llama-2-70b 4096 มล.g5.48xlarge
ลามะ-2-70b-แชท meta-textgeneration-ลามะ-2-70b-f 4096 มล.g5.48xlarge

โปรดทราบว่าตำแหน่งข้อมูล SageMaker มีขีดจำกัดการหมดเวลาอยู่ที่ 60 วินาที ดังนั้น แม้ว่าโมเดลอาจสามารถสร้างโทเค็นได้ 4096 รายการ แต่ถ้าการสร้างข้อความใช้เวลามากกว่า 60 วินาที คำขอจะล้มเหลว สำหรับรุ่น 7B, 13B และ 70B เราแนะนำให้ตั้งค่า max_new_tokens ไม่เกิน 1500, 1000 และ 500 ตามลำดับ ในขณะที่รักษาจำนวนโทเค็นทั้งหมดน้อยกว่า 4K

การอนุมานและตัวอย่างแจ้งสำหรับ Llama-2-70b

คุณสามารถใช้โมเดลลามะเพื่อเติมข้อความสำหรับข้อความส่วนใดก็ได้ ด้วยการสร้างข้อความ คุณสามารถทำงานต่างๆ ได้ เช่น การตอบคำถาม การแปลภาษา การวิเคราะห์ความรู้สึก และอื่นๆ อีกมากมาย เพย์โหลดที่ป้อนไปยังจุดสิ้นสุดมีลักษณะเหมือนรหัสต่อไปนี้:

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

ต่อไปนี้คือข้อความแจ้งตัวอย่างบางส่วนและข้อความที่สร้างขึ้นโดยโมเดล เอาต์พุตทั้งหมดถูกสร้างขึ้นด้วยพารามิเตอร์อนุมาน {"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] [

ในตัวอย่างถัดไป เราจะแสดงวิธีใช้โมเดลลามะด้วยการเรียนรู้ในบริบทแบบไม่กี่ช็อต ซึ่งเราได้ให้ตัวอย่างการฝึกอบรมสำหรับโมเดล โปรดทราบว่าเราจะอนุมานเฉพาะโมเดลที่นำไปใช้งานเท่านั้น และในระหว่างกระบวนการนี้ น้ำหนักของโมเดลจะไม่เปลี่ยนแปลง

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

การอนุมานและตัวอย่างแจ้งสำหรับ Llama-2-70b-chat

ด้วยโมเดล Llama-2-Chat ซึ่งปรับให้เหมาะกับกรณีการใช้งานการสนทนา การป้อนข้อมูลไปยังจุดสิ้นสุดของโมเดลการแชทคือประวัติก่อนหน้าระหว่างผู้ช่วยแชทและผู้ใช้ คุณสามารถถามคำถามตามบริบทของการสนทนาที่เกิดขึ้นจนถึงตอนนี้ คุณยังสามารถระบุการกำหนดค่าระบบ เช่น บุคลิกที่กำหนดพฤติกรรมของผู้ช่วยแชท เพย์โหลดอินพุตไปยังจุดสิ้นสุดมีลักษณะเหมือนรหัสต่อไปนี้:

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}
}

ต่อไปนี้คือข้อความแจ้งตัวอย่างบางส่วนและข้อความที่สร้างขึ้นโดยโมเดล เอาต์พุตทั้งหมดถูกสร้างขึ้นด้วยพารามิเตอร์การอนุมาน {"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!

ในตัวอย่างต่อไปนี้ ผู้ใช้ได้สนทนากับผู้ช่วยเกี่ยวกับสถานที่ท่องเที่ยวในปารีส ถัดไป ผู้ใช้กำลังสอบถามเกี่ยวกับตัวเลือกแรกที่ผู้ช่วยแชทแนะนำ

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

ในตัวอย่างต่อไปนี้ เราตั้งค่าคอนฟิกของระบบ:

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: 🇨🇳🛫🛬🇺🇸🗽🏙️🚕💨🛩️🛬🛫😴💤🛩️🛬🛫😍

ทำความสะอาด

หลังจากที่คุณเรียกใช้สมุดบันทึกเสร็จแล้ว อย่าลืมลบทรัพยากรทั้งหมด เพื่อให้ทรัพยากรทั้งหมดที่คุณสร้างในกระบวนการถูกลบและการเรียกเก็บเงินของคุณจะหยุดลง:

predictor.delete_model()
predictor.delete_endpoint()

สรุป

ในโพสต์นี้ เราได้แสดงวิธีเริ่มต้นใช้งานโมเดลลามะ 2 ใน SageMaker Studio ด้วยสิ่งนี้ คุณจะสามารถเข้าถึงโมเดลรองพื้น Llama 2 หกรุ่นที่มีพารามิเตอร์หลายพันล้านตัว เนื่องจากโมเดลพื้นฐานได้รับการฝึกอบรมล่วงหน้า จึงสามารถช่วยลดต้นทุนการฝึกอบรมและโครงสร้างพื้นฐาน และเปิดใช้งานการปรับแต่งสำหรับกรณีการใช้งานของคุณ หากต้องการเริ่มต้นใช้งาน SageMaker JumpStart โปรดไปที่แหล่งข้อมูลต่อไปนี้:


เกี่ยวกับผู้แต่ง

โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI.จูน วอน เป็นผู้จัดการผลิตภัณฑ์ของ SageMaker JumpStart เขามุ่งเน้นที่การสร้างแบบจำลองพื้นฐานที่ค้นพบได้ง่ายและใช้งานได้ เพื่อช่วยลูกค้าสร้างแอปพลิเคชัน AI เชิงกำเนิด ประสบการณ์ของเขาที่ Amazon ยังรวมถึงแอปพลิเคชันการช็อปปิ้งบนมือถือและการจัดส่งในระยะทางสุดท้าย

วิเวกมะดัน ดร.วิเวก มะดัน เป็นนักวิทยาศาสตร์ประยุกต์กับทีม Amazon SageMaker JumpStart เขาสำเร็จการศึกษาระดับปริญญาเอกจากมหาวิทยาลัยอิลลินอยส์ Urbana-Champaign และเป็นนักวิจัยหลังปริญญาเอกที่ Georgia Tech เขาเป็นนักวิจัยเชิงรุกด้านการเรียนรู้ของเครื่องและการออกแบบอัลกอริธึม และได้ตีพิมพ์เอกสารในการประชุม EMNLP, ICLR, COLT, FOCS และ SODA โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI. ดร.ไคล์ อูลริช เป็นนักวิทยาศาสตร์ประยุกต์กับทีม Amazon SageMaker JumpStart งานวิจัยที่เขาสนใจ ได้แก่ อัลกอริธึมแมชชีนเลิร์นนิงที่ปรับขนาดได้ คอมพิวเตอร์วิทัศน์ อนุกรมเวลา เบส์ที่ไม่ใช่พารามิเตอร์ และกระบวนการเกาส์เซียน ปริญญาเอกของเขามาจาก Duke University และเขาได้ตีพิมพ์บทความใน NeurIPS, Cell และ Neuron โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI. ดร. Ashish Khetan เป็นนักวิทยาศาสตร์ประยุกต์อาวุโสของ Amazon SageMaker JumpStart และช่วยพัฒนาอัลกอริทึมการเรียนรู้ของเครื่อง เขาได้รับปริญญาเอกจาก University of Illinois Urbana-Champaign เขาเป็นนักวิจัยที่กระตือรือร้นในด้านแมชชีนเลิร์นนิงและการอนุมานทางสถิติ และได้ตีพิมพ์บทความจำนวนมากในการประชุม NeurIPS, ICML, ICLR, JMLR, ACL และ EMNLP โมเดลรองพื้น Llama 2 จาก Meta พร้อมใช้งานแล้วใน Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain ข้อมูลอัจฉริยะ ค้นหาแนวตั้ง AI. ซุนดาร์ รังคนาธาน เป็นหัวหน้าระดับโลกของผู้เชี่ยวชาญ GenAI/Frameworks GTM ที่ AWS เขามุ่งเน้นไปที่การพัฒนากลยุทธ์ GTM สำหรับโมเดลภาษาขนาดใหญ่ GenAI และปริมาณงาน ML ขนาดใหญ่ในบริการต่างๆ ของ AWS เช่น Amazon EC2, EKS, EFA, AWS Batch และ Amazon SageMaker ประสบการณ์ของเขารวมถึงบทบาทความเป็นผู้นำในการจัดการผลิตภัณฑ์และการพัฒนาผลิตภัณฑ์ที่ NetApp, Micron Technology, Qualcomm และ Mentor Graphics

ประทับเวลา:

เพิ่มเติมจาก AWS Machine Learning AWS