میٹا سے لاما 2 فاؤنڈیشن ماڈلز اب ایمیزون سیج میکر جمپ اسٹارٹ میں دستیاب ہیں۔ ایمیزون ویب سروسز

میٹا سے لاما 2 فاؤنڈیشن ماڈلز اب ایمیزون سیج میکر جمپ اسٹارٹ میں دستیاب ہیں۔ ایمیزون ویب سروسز

آج، ہم یہ اعلان کرتے ہوئے پرجوش ہیں کہ میٹا کے تیار کردہ لاما 2 فاؤنڈیشن ماڈلز صارفین کے لیے دستیاب ہیں۔ ایمیزون سیج میکر جمپ اسٹارٹ. لاما 2 فیملی آف لارج لینگویج ماڈلز (LLMs) 7 بلین سے 70 بلین پیرامیٹرز کے پیمانے پر پہلے سے تربیت یافتہ اور ٹھیک ٹیونڈ جنریٹو ٹیکسٹ ماڈلز کا مجموعہ ہے۔ فائن ٹیونڈ LLMs، جسے Llama-2-chat کہا جاتا ہے، ڈائیلاگ کے استعمال کے معاملات کے لیے موزوں ہیں۔ آپ آسانی سے ان ماڈلز کو آزما سکتے ہیں اور انہیں SageMaker JumpStart کے ساتھ استعمال کر سکتے ہیں، جو کہ ایک مشین لرننگ (ML) مرکز ہے جو الگورتھم، ماڈلز، اور ML سلوشنز تک رسائی فراہم کرتا ہے تاکہ آپ ML کے ساتھ تیزی سے شروعات کر سکیں۔

اس پوسٹ میں، ہم SageMaker JumpStart کے ذریعے Llama 2 ماڈلز کو استعمال کرنے کے طریقہ پر چلتے ہیں۔

لاما 2 کیا ہے؟

Llama 2 ایک خودکار رجعت پسند زبان کا ماڈل ہے جو ایک بہتر ٹرانسفارمر فن تعمیر کا استعمال کرتا ہے۔ Llama 2 انگریزی میں تجارتی اور تحقیقی استعمال کے لیے ہے۔ یہ پیرامیٹر سائز کی ایک رینج میں آتا ہے — 7 بلین، 13 بلین، اور 70 بلین — نیز پہلے سے تربیت یافتہ اور ٹھیک ٹیونڈ تغیرات۔ میٹا کے مطابق، ٹیون شدہ ورژنز سپروائزڈ فائن ٹیوننگ (SFT) اور ہیومن فیڈ بیک (RLHF) کے ساتھ کمک سیکھنے کا استعمال کرتے ہیں تاکہ مدد اور حفاظت کے لیے انسانی ترجیحات کے مطابق ہوں۔ لاما 2 کو عوامی طور پر دستیاب ذرائع سے ڈیٹا کے 2 ٹریلین ٹوکنز پر پہلے سے تربیت دی گئی تھی۔ ٹیون شدہ ماڈلز اسسٹنٹ کی طرح چیٹ کے لیے بنائے گئے ہیں، جبکہ پہلے سے تربیت یافتہ ماڈلز کو قدرتی زبان کی تخلیق کے مختلف کاموں کے لیے ڈھالا جا سکتا ہے۔ اس سے قطع نظر کہ ایک ڈویلپر ماڈل کا کون سا ورژن استعمال کرتا ہے، میٹا کی طرف سے ذمہ دار استعمال گائیڈ اضافی فائن ٹیوننگ کی رہنمائی میں مدد کر سکتا ہے جو مناسب حفاظتی تخفیف کے ساتھ ماڈلز کو اپنی مرضی کے مطابق اور بہتر بنانے کے لیے ضروری ہو سکتا ہے۔

سیج میکر جمپ اسٹارٹ کیا ہے؟

With SageMaker JumpStart, ML practitioners can choose from a broad selection of open source foundation models. ML practitioners can deploy foundation models to dedicated ایمیزون سیج میکر نیٹ ورک الگ تھلگ ماحول سے مثالیں اور ماڈل ٹریننگ اور تعیناتی کے لیے SageMaker کا استعمال کرتے ہوئے ماڈلز کو اپنی مرضی کے مطابق بنائیں۔

اب آپ چند کلکس کے ساتھ لاما 2 کو دریافت اور تعینات کر سکتے ہیں۔ ایمیزون سیج میکر اسٹوڈیو یا پروگرامی طور پر SageMaker Python SDK کے ذریعے، آپ کو SageMaker خصوصیات کے ساتھ ماڈل کی کارکردگی اور MLOps کنٹرول حاصل کرنے کے قابل بناتا ہے جیسے ایمیزون سیج میکر پائپ لائنز, ایمیزون سیج میکر ڈیبگر، یا کنٹینر لاگز۔ ماڈل کو AWS محفوظ ماحول میں اور آپ کے VPC کنٹرولز کے تحت تعینات کیا گیا ہے، جو ڈیٹا کی حفاظت کو یقینی بنانے میں مدد کرتا ہے۔ لاما 2 ماڈل آج ایمیزون سیج میکر اسٹوڈیو میں دستیاب ہیں، ابتدائی طور پر us-east 1 اور us-west 2 خطوں.

ماڈلز دریافت کریں۔

آپ SageMaker Studio UI اور SageMaker Python SDK میں SageMaker JumpStart کے ذریعے فاؤنڈیشن ماڈلز تک رسائی حاصل کر سکتے ہیں۔ اس سیکشن میں، ہم سیج میکر اسٹوڈیو میں ماڈلز کو دریافت کرنے کا طریقہ دیکھتے ہیں۔

سیج میکر اسٹوڈیو ایک مربوط ترقیاتی ماحول (IDE) ہے جو ایک واحد ویب پر مبنی بصری انٹرفیس فراہم کرتا ہے جہاں آپ ڈیٹا کی تیاری سے لے کر اپنے ML ماڈلز کی تعمیر، تربیت، اور تعیناتی تک تمام ML ترقیاتی مراحل کو انجام دینے کے لیے مقصد کے لیے بنائے گئے ٹولز تک رسائی حاصل کر سکتے ہیں۔ شروع کرنے اور SageMaker اسٹوڈیو کو ترتیب دینے کے طریقے کے بارے میں مزید تفصیلات کے لیے، رجوع کریں۔ ایمیزون سیج میکر اسٹوڈیو.

سیج میکر اسٹوڈیو پر آنے کے بعد، آپ سیج میکر جمپ اسٹارٹ تک رسائی حاصل کر سکتے ہیں، جس میں پہلے سے تربیت یافتہ ماڈلز، نوٹ بکس اور پہلے سے تیار کردہ حل شامل ہیں۔ پہلے سے تعمیر شدہ اور خودکار حل.

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

سیج میکر جمپ اسٹارٹ لینڈنگ پیج سے، آپ حل، ماڈل، نوٹ بک اور دیگر وسائل کو براؤز کر سکتے ہیں۔ آپ کو دو فلیگ شپ لاما 2 ماڈل مل سکتے ہیں۔ فاؤنڈیشن ماڈل: ٹیکسٹ جنریشن carousel. If you don’t see Llama 2 models, update your SageMaker Studio version by shutting down and restarting. For more information about version updates, refer to اسٹوڈیو ایپس کو بند کریں اور اپ ڈیٹ کریں۔.

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

آپ دیگر چار ماڈل کی مختلف حالتیں بھی منتخب کر کے تلاش کر سکتے ہیں۔ تمام ٹیکسٹ جنریشن ماڈلز کو دریافت کریں۔ یا تلاش کرنا llama تلاش کے باکس میں.

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

آپ ماڈل کے بارے میں تفصیلات دیکھنے کے لیے ماڈل کارڈ کا انتخاب کر سکتے ہیں جیسے کہ لائسنس، تربیت کے لیے استعمال ہونے والا ڈیٹا، اور استعمال کرنے کا طریقہ۔ آپ کو دو بٹن بھی مل سکتے ہیں، تعینات اور نوٹ بک کھولیں۔، جو آپ کو ماڈل استعمال کرنے میں مدد کرتا ہے۔

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

جب آپ کسی بھی بٹن کا انتخاب کرتے ہیں، تو ایک پاپ اپ اختتامی صارف کے لائسنس کا معاہدہ اور آپ کو تسلیم کرنے کے لیے قابل قبول استعمال کی پالیسی دکھائے گا۔

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

تسلیم کرنے پر، آپ ماڈل کو استعمال کرنے کے لیے اگلے مرحلے پر جائیں گے۔

ایک ماڈل تعینات کریں۔

جب آپ کا انتخاب کریں تعینات اور شرائط کو تسلیم کریں، ماڈل کی تعیناتی شروع ہو جائے گی۔ متبادل طور پر، آپ مثال کے نوٹ بک کے ذریعے تعینات کر سکتے ہیں جو منتخب کر کے ظاہر ہوتی ہے۔ نوٹ بک کھولیں۔. مثال کی نوٹ بک اختتام سے آخر تک رہنمائی فراہم کرتی ہے کہ اندازہ کے لیے ماڈل کو کیسے تعینات کیا جائے اور وسائل کو صاف کیا جائے۔

نوٹ بک کا استعمال کرتے ہوئے تعینات کرنے کے لیے، ہم ایک مناسب ماڈل کو منتخب کرکے شروع کرتے ہیں، جس کی وضاحت کی گئی ہے۔ model_id. آپ مندرجہ ذیل کوڈ کے ساتھ SageMaker پر کسی بھی منتخب ماڈل کو تعینات کر سکتے ہیں:

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

یہ ماڈل کو ڈیفالٹ کنفیگریشنز کے ساتھ SageMaker پر تعینات کرتا ہے، بشمول ڈیفالٹ مثال کی قسم اور ڈیفالٹ VPC کنفیگریشنز۔ آپ ان کنفیگریشنز کو غیر ڈیفالٹ ویلیوز بتا کر تبدیل کر سکتے ہیں۔ جمپ اسٹارٹ ماڈل. اس کے تعینات ہونے کے بعد، آپ SageMaker پیشن گوئی کے ذریعے تعینات اختتامی نقطہ کے خلاف تخمینہ چلا سکتے ہیں:

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}
}

فائن ٹیون شدہ چیٹ ماڈلز (Llama-2-7b-chat, Llama-2-13b-chat, Llama-2-70b-chat) صارف اور چیٹ اسسٹنٹ کے درمیان چیٹ کی تاریخ کو قبول کرتے ہیں، اور بعد میں چیٹ تیار کرتے ہیں۔ پہلے سے تربیت یافتہ ماڈلز (Llama-2-7b, Llama-2-13b, Llama-2-70b) کو سٹرنگ پرامپٹ کی ضرورت ہوتی ہے اور فراہم کردہ پرامپٹ پر متن کی تکمیل کو انجام دیتے ہیں۔ درج ذیل کوڈ دیکھیں:

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

نوٹ کریں کہ بطور ڈیفالٹ، accept_eula جھوٹ پر سیٹ ہے. آپ کو سیٹ کرنے کی ضرورت ہے۔ accept_eula=true اختتامی نقطہ کو کامیابی سے شروع کرنے کے لیے۔ ایسا کرنے سے، آپ صارف کے لائسنس کے معاہدے اور قابل قبول استعمال کی پالیسی کو قبول کرتے ہیں جیسا کہ پہلے ذکر کیا گیا ہے۔ آپ بھی ڈاؤن لوڈ، اتارنا لائسنس کا معاہدہ.

Custom_attributes EULA کو پاس کرنے کے لیے استعمال کیا جاتا ہے کلیدی/قدر کے جوڑے۔ کلید اور قدر کو الگ کیا جاتا ہے۔ = اور جوڑے الگ ہوتے ہیں۔ ;. اگر صارف ایک ہی کلید کو ایک سے زیادہ بار پاس کرتا ہے، تو آخری قدر رکھی جاتی ہے اور اسکرپٹ ہینڈلر کو بھیج دی جاتی ہے (یعنی اس صورت میں، مشروط منطق کے لیے استعمال کیا جاتا ہے)۔ مثال کے طور پر، اگر accept_eula=false; accept_eula=true پھر سرور کو منتقل کیا جاتا ہے۔  accept_eula=true رکھا جاتا ہے اور اسکرپٹ ہینڈلر کو دیا جاتا ہے۔

انفرنس پیرامیٹرز اختتامی نقطہ پر ٹیکسٹ جنریشن کے عمل کو کنٹرول کرتے ہیں۔ زیادہ سے زیادہ نئے ٹوکن کنٹرول سے مراد ماڈل کے ذریعہ تیار کردہ آؤٹ پٹ کا سائز ہے۔ نوٹ کریں کہ یہ الفاظ کی تعداد کے برابر نہیں ہے کیونکہ ماڈل کی الفاظ انگریزی زبان کے الفاظ کے برابر نہیں ہیں، اور ہر ٹوکن انگریزی زبان کا لفظ نہیں ہو سکتا۔ درجہ حرارت آؤٹ پٹ میں بے ترتیب پن کو کنٹرول کرتا ہے۔ اعلی درجہ حرارت کے نتیجے میں زیادہ تخلیقی اور فریب کاری پیدا ہوتی ہے۔ تمام قیاس کے پیرامیٹرز اختیاری ہیں۔

درج ذیل جدول میں سیج میکر جمپ سٹارٹ کے ساتھ دستیاب تمام لاما ماڈلز کی فہرست دی گئی ہے۔ model_ids, پہلے سے طے شدہ مثال کی اقسام، اور کل ٹوکنز کی زیادہ سے زیادہ تعداد (ان پٹ ٹوکنز کی تعداد اور جنریٹڈ ٹوکنز کی تعداد) ان میں سے ہر ایک ماڈل کے لیے تعاون یافتہ ہے۔

ماڈل کا نام ماڈل کی شناخت زیادہ سے زیادہ کل ٹوکن پہلے سے طے شدہ مثال کی قسم
للہ -2-7b meta-textgeneration-llama-2-7b 4096 ml.g5.2xlarge
Llama-2-7b-چیٹ meta-textgeneration-llama-2-7b-f 4096 ml.g5.2xlarge
للہ -2-13b meta-textgeneration-llama-2-13b 4096 ml.g5.12xlarge
Llama-2-13b-چیٹ meta-textgeneration-llama-2-13b-f 4096 ml.g5.12xlarge
للہ -2-70b meta-textgeneration-llama-2-70b 4096 ml.g5.48xlarge
Llama-2-70b-چیٹ meta-textgeneration-llama-2-70b-f 4096 ml.g5.48xlarge

نوٹ کریں کہ SageMaker اینڈ پوائنٹس کی ٹائم آؤٹ کی حد 60s ہے۔ اس طرح، اگرچہ ماڈل 4096 ٹوکن بنانے کے قابل ہو سکتا ہے، اگر ٹیکسٹ جنریشن میں 60 سے زیادہ وقت لگتا ہے، تو درخواست ناکام ہو جائے گی۔ 7B، 13B، اور 70B ماڈلز کے لیے، ہم سیٹ کرنے کی تجویز کرتے ہیں۔ max_new_tokens ٹوکنز کی کل تعداد کو 1500K سے کم رکھتے ہوئے بالترتیب 1000، 500 اور 4 سے زیادہ نہیں۔

Llama-2-70b کے لیے اشارہ اور مثال کا اشارہ

آپ متن کے کسی بھی ٹکڑے کے لیے متن کی تکمیل کے لیے Llama ماڈل استعمال کر سکتے ہیں۔ ٹیکسٹ جنریشن کے ذریعے، آپ متعدد کام انجام دے سکتے ہیں، جیسے سوالات کے جوابات، زبان کا ترجمہ، جذبات کا تجزیہ، اور بہت کچھ۔ اختتامی نقطہ پر ان پٹ پے لوڈ درج ذیل کوڈ کی طرح لگتا ہے:

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

ذیل میں نمونے کے کچھ نمونے کے اشارے اور ماڈل کے ذریعہ تیار کردہ متن ہیں۔ تمام آؤٹ پٹ انفرنس پیرامیٹرز کے ساتھ تیار کیے جاتے ہیں۔ {"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] [

اگلی مثال میں، ہم دکھاتے ہیں کہ لاما ماڈلز کو چند شاٹ ان سیاق و سباق سیکھنے کے ساتھ کیسے استعمال کیا جائے، جہاں ہم ماڈل کو دستیاب تربیتی نمونے فراہم کرتے ہیں۔ نوٹ کریں کہ ہم صرف تعینات کردہ ماڈل کا اندازہ لگاتے ہیں اور اس عمل کے دوران، ماڈل کا وزن تبدیل نہیں ہوتا ہے۔

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-chat کے لیے اشارہ اور مثال کا اشارہ

Llama-2-Chat ماڈلز کے ساتھ، جو ڈائیلاگ کے استعمال کے کیسز کے لیے بہتر بنائے گئے ہیں، چیٹ ماڈل کے اختتامی پوائنٹس کا ان پٹ چیٹ اسسٹنٹ اور صارف کے درمیان پچھلی تاریخ ہے۔ آپ اب تک ہونے والی گفتگو سے متعلقہ سوالات پوچھ سکتے ہیں۔ آپ سسٹم کنفیگریشن بھی فراہم کر سکتے ہیں، جیسے کہ وہ شخصیات جو چیٹ اسسٹنٹ کے رویے کی وضاحت کرتی ہیں۔ اختتامی نقطہ پر ان پٹ پے لوڈ درج ذیل کوڈ کی طرح لگتا ہے:

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}
}

ذیل میں نمونے کے کچھ نمونے کے اشارے اور ماڈل کے ذریعہ تیار کردہ متن ہیں۔ تمام آؤٹ پٹ انفرنس پیرامیٹرز کے ساتھ تیار کیے جاتے ہیں۔ {"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!

مندرجہ ذیل مثال میں، صارف نے اسسٹنٹ کے ساتھ پیرس میں سیاحتی مقامات کے بارے میں بات چیت کی ہے۔ اگلا، صارف چیٹ اسسٹنٹ کے ذریعہ تجویز کردہ پہلے آپشن کے بارے میں پوچھتا ہے۔

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

مندرجہ ذیل مثالوں میں، ہم سسٹم کی کنفیگریشن سیٹ کرتے ہیں:

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: 🇨🇳🛫🛬🇺🇸🗽🏙️🚕💨🛩️🛬🛫😴💤🛩️🛬🛫😍

صاف کرو

نوٹ بک چلانے کے بعد، تمام وسائل کو حذف کرنا یقینی بنائیں تاکہ اس عمل میں آپ کے بنائے گئے تمام وسائل حذف ہو جائیں اور آپ کی بلنگ روک دی جائے:

predictor.delete_model()
predictor.delete_endpoint()

نتیجہ

اس پوسٹ میں، ہم نے آپ کو دکھایا کہ سیج میکر اسٹوڈیو میں لاما 2 ماڈلز کے ساتھ کیسے آغاز کیا جائے۔ اس کے ساتھ، آپ کو چھ Llama 2 فاؤنڈیشن ماڈلز تک رسائی حاصل ہے جو اربوں پیرامیٹرز پر مشتمل ہے۔ چونکہ فاؤنڈیشن ماڈل پہلے سے تربیت یافتہ ہوتے ہیں، اس لیے وہ تربیت اور بنیادی ڈھانچے کے اخراجات کو کم کرنے میں بھی مدد کر سکتے ہیں اور آپ کے استعمال کے معاملے کے لیے حسب ضرورت کو فعال کر سکتے ہیں۔ SageMaker JumpStart کے ساتھ شروع کرنے کے لیے، درج ذیل وسائل ملاحظہ کریں:


مصنفین کے بارے میں

Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai.جون جیت گیا۔ سیج میکر جمپ اسٹارٹ کے ساتھ پروڈکٹ مینیجر ہے۔ وہ فاؤنڈیشن ماڈلز کو آسانی سے قابل دریافت اور قابل استعمال بنانے پر توجہ مرکوز کرتا ہے تاکہ صارفین کو تخلیقی AI ایپلی کیشنز بنانے میں مدد مل سکے۔ ایمیزون پر اس کے تجربے میں موبائل شاپنگ ایپلی کیشن اور آخری میل کی ترسیل بھی شامل ہے۔

وویک مدن ڈاکٹر وویک مدن Amazon SageMaker جمپ سٹارٹ ٹیم کے ساتھ ایک اپلائیڈ سائنٹسٹ ہے۔ انہوں نے Urbana-Champaign میں یونیورسٹی آف الینوائے سے پی ایچ ڈی کی اور جارجیا ٹیک میں پوسٹ ڈاکٹریٹ ریسرچر تھے۔ وہ مشین لرننگ اور الگورتھم ڈیزائن میں ایک فعال محقق ہے اور اس نے EMNLP، ICLR، COLT، FOCS، اور SODA کانفرنسوں میں مقالے شائع کیے ہیں۔ Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai. ڈاکٹر کائل الریچ Amazon SageMaker جمپ سٹارٹ ٹیم کے ساتھ ایک اپلائیڈ سائنٹسٹ ہے۔ اس کی تحقیقی دلچسپیوں میں توسیع پذیر مشین لرننگ الگورتھم، کمپیوٹر ویژن، ٹائم سیریز، بایسیئن نان پیرامیٹرکس، اور گاوسی عمل شامل ہیں۔ اس کی پی ایچ ڈی ڈیوک یونیورسٹی سے ہے اور اس نے نیور آئی پی ایس، سیل اور نیوران میں مقالے شائع کیے ہیں۔ Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai. ڈاکٹر آشیش کھیتان Amazon SageMaker JumpStart کے ساتھ ایک سینئر اپلائیڈ سائنٹسٹ ہے اور مشین لرننگ الگورتھم تیار کرنے میں مدد کرتا ہے۔ انہوں نے یونیورسٹی آف الینوائے اربانا-چمپین سے پی ایچ ڈی کی۔ وہ مشین لرننگ اور شماریاتی اندازہ میں ایک فعال محقق ہے، اور اس نے NeurIPS، ICML، ICLR، JMLR، ACL، اور EMNLP کانفرنسوں میں بہت سے مقالے شائع کیے ہیں۔ Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart | Amazon Web Services PlatoBlockchain Data Intelligence. Vertical Search. Ai. سندر رنگناتھن AWS میں GenAI/Frameworks GTM ماہرین کے عالمی سربراہ ہیں۔ وہ بڑے لینگویج ماڈلز، GenAI، اور AWS سروسز جیسے Amazon EC2، EKS، EFA، AWS Batch، اور Amazon SageMaker میں بڑے پیمانے پر ML ورک بوجھ کے لیے GTM حکمت عملی تیار کرنے پر توجہ مرکوز کرتا ہے۔ اس کے تجربے میں NetApp، Micron Technology، Qualcomm، اور Mentor Graphics میں پروڈکٹ مینجمنٹ اور مصنوعات کی ترقی میں قائدانہ کردار شامل ہیں۔

ٹائم اسٹیمپ:

سے زیادہ AWS مشین لرننگ