Recommended
Recommended
More Related Content
Similar to Cloud Study Jam[1st OCT] gdscgtbit.pptx
Similar to Cloud Study Jam[1st OCT] gdscgtbit.pptx (20)
Recently uploaded
Recently uploaded (20)
Cloud Study Jam[1st OCT] gdscgtbit.pptx
- 1. Google Cloud Study Jams Mukal Dadhwal Facilitator GCSJ, GDSC GTBIT GTBIT
- 2. What is Google Cloud Study Jam? • Google Cloud Study Jams will provide students an opportunity to kickstart their learning on Cloud technology. • The goal is to teach developers cloud skills using Google Cloud Platform through hands-on technical labs and tutorials. • Participants get free access to Qwiklabs for one month to complete hands- on labs. Those who complete designated labs receive Google Cloud badges and rewards. • Expand your learnings and be industry-ready!
- 4. Learning about Cloud and its Services
- 5. What is cloud? â—Ź Cloud technology essentially refers to the delivery of computing services - servers, storage, databases, networking, software, analytics and more - over the Internet ("the cloud") to offer faster innovation, flexible resources and economies of scale â—Ź Take the analogy of a small office having very cramped office space â—Ź Similarly cloud also rents us some storage and computing resources by giving a price. As the usage increases more resources will be utilised and more price will be paid
- 8. Google Cloud Storage â—Ź Google Cloud Storage is an object storage service that allows users to store and retrieve data in the form of objects â—Ź It provides highly scalable, durable, and secure storage for various types of data, including documents, images, and multimedia content. Google Cloud Datastore & SQL Datastore â—Ź This services provide NoSQL document/collection model and SQL tables for building highly scalable and consistent applications â—Ź It automatically handles sharding and replication, providing a robust and flexible storage solution for structured data
- 10. Google Compute Engine â—Ź Google Compute Engine is an Infrastructure as a Service (IaaS) that allows users to run virtual machines (VMs) on Google's infrastructure. â—Ź It provides scalable and flexible computing resources for running various workloads Google App Engine â—Ź Google App Engine is a Platform as a Service (PaaS) that enables developers to build and deploy applications without managing the underlying infrastructure â—Ź It supports multiple programming languages and automatically scales based on demand.
- 11. Google BigQuery â—Ź Google BigQuery is a serverless, highly scalable, and cost-effective data warehouse and analytics service. â—Ź It allows users to run fast SQL queries on large datasets and analyze data in real-time, making it ideal for business intelligence and data analysis Google AI/ML Services â—Ź Vertex AI is Google's flagship AI/ML platform. It allows you to train ML models, host trained models, and make predictions using those models â—Ź You can train models using TensorFlow, scikit-learn, XGBoost, and custom containers. Vertex AI also offers AutoML capabilities to automate the model training process
- 12. Generative AI
- 13. We’re in an AI-driven revolution Source: AI: Recent Trends and Applications, Emerging Communication and Computing Steam Power 1784 Electricity 1870 Information Technology 1969 Artificial Intelligence Today A I
- 14. This revolution started at Google and we continue to innovate Responsible AI at the foundation Google invents Transformer kickstarting LLM revolution Google’s groundbreaking large language model, BERT AlphaFold predicts structures of all known proteins Text-to-Text Transfer Transformer LLM 10B P model open sourced Google LaMDA model trained to converse Google PaLM single model to generalize across domains A conversational AI Service powered by LaMDA.
- 15. Proprietary + Confidential What is a Large Language Model?
- 16. Traditional programming Wave of neural networks ~2012 Cat: type: animal legs: 4 ears: 2 fur: yes likes: yarn, catnip (etc …) This is a cat. This is not a cat. Is this a cat? Yes So, you’ve learned about cats and millions of other concepts … what’s a cat? Proprietary + Confidential Go read this huuuuuuge pile of books. A cat is … Generative language models LaMDA, PaLM, GPT-3, etc.
- 17. Proprietary + Confidential First, some vocabulary Generative Model: An ML model that produces content, including language, code, imagery, music, video, etc. Large Language Model: machine learning models that are really good at understanding and generating human language. Large refers to both size and complexity of the neural network itself, as well as the size of the dataset it was trained on. Can also be used for non-generative language tasks (eg classification) Transformer: The neural network architecture underlying most of today’s generative models (and, more widely, most SOTA ML models). Published by Google in 2017.
- 18. Proprietary + Confidential Prompt: the text you feed to your model Prompt Design: The art and science of figuring out what text to feed your language model to get it to take on the behavior you want.
- 19. Proprietary + Confidential What is a language model? Write a poem about Cricket Cricket, oh cricket, game of my heart, Where legends are born and dreams start. With bat and ball, we play as one, Under the sun, until the day is done. From the village green to the grandest stage, Cricket unites us, age after age. With every run, we cheer and shout, As our heroes make us proud. … Zero- shot
- 20. Proprietary + Confidential Give examples Convert from english to french. peppermint : menthe poivrée desert cactus : cactus du désert potato : pomme de terre onion : oignon Few- shot
- 21. Proprietary + Confidential Give examples Convert Python to Javascript. Python: print("hello world") Javascript: console.log("hello world") Python: for x in range(0, 100): Javascript: Few- shot
- 22. Proprietary + Confidential Give examples Convert Python to Javascript. Python: print("hello world") Javascript: console.log("hello world") Python: for x in range(0, 100): Javascript: Few- shot EXAMPLE
- 23. Proprietary + Confidential Give examples Convert Python to Javascript. Python: print("hello world") Javascript: console.log("hello world") Python: for x in range(0, 100): Javascript:for (var x = 0; x < 100; x++) Few- shot
- 24. Proprietary + Confidential Prompt Design is tricky The art and science of figuring out what text to feed your language model to get it to take on the behavior you want.
- 25. Proprietary + Confidential A few observations: 1. LLMs are designed to predict the next word in a sequence. They are not required to be “truthful” when doing so. 2. LLMs can generate plausible-looking statements that are irrelevant or factually incorrect. 3. Hallucinations: LLM’s can generate false statements.
- 26. Proprietary + Confidential Temperature Temperature is a number used to tune the degree of randomness. Lower temperature →less randomness ● Temperature of 0 is deterministic (greed decoding) ● Generally better for tasks like q&a and summarization where you expect a more “correct” answer ● If you notice the model repeating itself, the temp is probably too low High temperature → more randomness ● Can result in more unusual (you might even say creative) response ● If you notice the model going off topic or being nonsensical, the temp is likely too high
- 27. What are large language models? ML algorithms that can recognize, predict, and generate human languages Pre-trained on petabyte scale text-based datasets resulting in large models with 10s to 100s of billions of parameters LLMs are normally pre-trained on a large corpus of text followed by fine-tuning on a specific task Go read this huuuuuuge pile of books. So, you’ve learned about cats and millions of other concepts … what’s a cat? A cat is a small, domesticated carnivorous mammal. Generative language models LaMDA, PaLM, GPT-3, etc. LLMs can also be called Large Models (includes all types of data modality) and Generative AI (a model that produces content)
- 28. Proprietary + Confidential LLM applications in industry Customer Support â—Ź Interactive Humanlike Chatbots â—Ź Conversation summarization for agents â—Ź Sentiment Analysis and Entity extraction Technology â—Ź Generating Code Snippets from description â—Ź Code Translation between languages â—Ź Auto Generated Documentation from Code Financial Services â—Ź Auto-generated summary of documents â—Ź Entity Extraction from KYC documents HealthCare â—Ź Domain specific entity extraction â—Ź Case documentation summary Retail â—Ź Generating product descriptions Media and Gaming â—Ź Designing game storylines, scripts â—Ź Auto Generated blogs, articles, and tweets â—Ź Grammar Correction and text-formatting
- 29. Proprietary + Confidential Traditional ML Dev â—Ź Needs 1000+ training examples to get started â—Ź Needs ML expertise (probably) â—Ź Needs compute time + hardware â—Ź Thinks about minimizing a loss function â—Ź Needs 0 training examples* â—Ź Does not need ML expertise* â—Ź Does not need to train a model* â—Ź Thinks about prompt design LLM Dev *To get started
- 31. Consumers & enterprises have different needs…. Plan a 3 day trip to Patagonia Create a valentine poem. A picture of a panda playing yahtzee How to make GF pancakes? I want to write a novel. How do I get started? Create a jazz song for a bday card How do we control our data How do we deal with fraud & security We need to be accurate & explainabl e How do we integrate our existing data & applications How will we control costs? Bard + MakerSuite Vertex AI + Duet AI Consumer s Enterprise s
- 32. Foundation Models Vertex AI End-to-End ML Platform Generative Al App Builder Tex t Chat Code Imag e Video Google Cloud Infrastructure - GPUs/TPUs Contact Center AI Healthcare AI Discovery AI Document AI Conversation AI Enterprise Search Foundation Models Business Users AI Practitioners Developer s Audio and Music Generative AI Studio Generative AI APIs Model Garden Cloud AI Portfolio To support the needs of Generative AI centric enterprise development Duet Al for Google Workspace Duet Al for Google Cloud
- 33. Duet AI for Google Workspace Enterprise Helps you write in Gmail and Docs Duet AI works behind the scenes to help you write — whether it’s refining existing work or helping you get started Helps you visualize in Slides With Duet AI, you can easily create images for presentations and meetings from a simple prompt Helps you organize in Sheets Duet AI is here to help you organize, classify and analyze your data faster than ever before Helps you connect in Meet Duet AI helps you look and sound your best on video calls so you can focus on the conversation
- 34. Roadmap for the coming month
- 36. Incentives?
- 37. Incentives?
- 38. Incentives? BADGES UPON COMPLETION OF YOUR PATHWAYS
- 39. IMPORTANT POINTERS TO REMEMBER ● Don’t engage in making notes ● Cover the topics which are easy to understand and intuitive first ● Use google chrome at its latest version for attending labs ● Videos link for labs will be shared with you so that you can watch them whenever you are stuck ● Don’t try to become an expert, Be a learner!
- 40. QnA
- 41. Thank You