- 233
- 80 671
SAI KUMAR REDDY
India
Приєднався 9 кві 2022
Hello all, I am going to upload videos related to Python, Data Science, Machine Learning, and other interesting AI technologies. I will definitely try to explain the latest technologies I know. and how to use them. and help to solve the bugs we face while learning programming and other technological issues. so guys kindly support my UA-cam channel and if you have any queries or issues related to topics I Teach can comment below. I will be glad to help with it..
Thank You....do like share and subscribe...
Business Email - sktech.programming@gmail.com
Thank You....do like share and subscribe...
Business Email - sktech.programming@gmail.com
Understanding Decoders in Transformers | Key to AI Advancements | Attention is All You Need #decoder
#transformers #generativepretrainedtransformer #decoder #attentionisallyouneed
Welcome to our deep dive into the world of Transformers! In this video, we explore the crucial role of decoders in transformer architecture, one of the most powerful models in Natural Language Processing (NLP).
🔍 What You'll Learn:
The fundamental structure of decoders in Transformers
How decoders differ from encoders and their specific functions
Practical applications of decoders in real-world NLP tasks
Step-by-step breakdown of the decoder's components, including masked multi-head attention and feed-forward networks
Tips for implementing decoders in your own machine learning projects
Whether you're a beginner wanting to understand the basics or an advanced practitioner looking for deeper insights, this video has something for everyone!
Don't forget to like, subscribe, and hit the notification bell for more content on NLP and machine learning!
Business email id- sktech.programming@gmail.com
do mail here
For Guidance - topmate.io/sai_kumar_reddy_n?SocialProfile
Join this channel to get access to the perks:
ua-cam.com/channels/hiEiQ2E3_DUGYDG340si-A.htmljoin
Python Video- ua-cam.com/video/dD7hg_qvtD8/v-deo.htmlsi=EzYhcYrXZ8EKbvKf
Transformers GitHub Link - github.com/ApexIQ/NLP_Concepts
Do Support the channel friends.
telegram link- t.me/saikumarreddyYT
article link- medium.com/@saikumarreddy_45969/oops-02-inheritance-2c498eba3689
And also Guys follow me on social media links are available below.
Instagram- sai_kumar_datascientist
LinkedIn- www.linkedin.com/in/sai-kumar-reddy-n-data-scientist/
twitter- 123saikumar9036
#Transformers #ArtificialIntelligence #MachineLearning #DeepLearning #AI #NLP #TransformersExplained #GPT #BERT #DeepLearningTutorial
#transformers
#decoder
#maskedmultiheadattention
#deeplearning
#machinelearning
#nlp
#googleai
#artificialintelligence
#tech
#tutorial
#artificialintelligence
#tech
#tutorial
Welcome to our deep dive into the world of Transformers! In this video, we explore the crucial role of decoders in transformer architecture, one of the most powerful models in Natural Language Processing (NLP).
🔍 What You'll Learn:
The fundamental structure of decoders in Transformers
How decoders differ from encoders and their specific functions
Practical applications of decoders in real-world NLP tasks
Step-by-step breakdown of the decoder's components, including masked multi-head attention and feed-forward networks
Tips for implementing decoders in your own machine learning projects
Whether you're a beginner wanting to understand the basics or an advanced practitioner looking for deeper insights, this video has something for everyone!
Don't forget to like, subscribe, and hit the notification bell for more content on NLP and machine learning!
Business email id- sktech.programming@gmail.com
do mail here
For Guidance - topmate.io/sai_kumar_reddy_n?SocialProfile
Join this channel to get access to the perks:
ua-cam.com/channels/hiEiQ2E3_DUGYDG340si-A.htmljoin
Python Video- ua-cam.com/video/dD7hg_qvtD8/v-deo.htmlsi=EzYhcYrXZ8EKbvKf
Transformers GitHub Link - github.com/ApexIQ/NLP_Concepts
Do Support the channel friends.
telegram link- t.me/saikumarreddyYT
article link- medium.com/@saikumarreddy_45969/oops-02-inheritance-2c498eba3689
And also Guys follow me on social media links are available below.
Instagram- sai_kumar_datascientist
LinkedIn- www.linkedin.com/in/sai-kumar-reddy-n-data-scientist/
twitter- 123saikumar9036
#Transformers #ArtificialIntelligence #MachineLearning #DeepLearning #AI #NLP #TransformersExplained #GPT #BERT #DeepLearningTutorial
#transformers
#decoder
#maskedmultiheadattention
#deeplearning
#machinelearning
#nlp
#googleai
#artificialintelligence
#tech
#tutorial
#artificialintelligence
#tech
#tutorial
Переглядів: 37
Відео
Conditional Statements In Python | if, elif & else statements In Python | Python Simplified 2024
Переглядів 5414 годин тому
#pythoncourses #coding #pythonprogramming #pythontutorial #python3 #pythonforbeginners #conditionalstatements #if #else #elif Hello Viewers, In this video I have explained In detail about starting Python and how to learn in 2024. do check out the video completely. and do like share and subscribe to the channel. I have also created a BOOK regarding it. the book link is available below. Business ...
A Deep Dive into Masked Multi-Head Attention in the Decoder | Key to AI Advancements | Transformers
Переглядів 58День тому
#transformers #generativeai #llm #ai In this seventh installment of our Transformers series, we'll explore the decoder architecture and its key component: masked multi-head attention. Learn how this mechanism prevents the model from seeing future tokens during decoding, ensuring that the generated output is coherent and contextually relevant 👉 Don't miss the next episode! Hit the notification b...
Mastering Transformer Encoders | Key to AI Advancements | Transformers Simplified #transformers
Переглядів 5014 днів тому
#transformers #generativeai #llm #ai Unlock the secrets of the Encoder in the Transformer Architecture-the backbone of many advanced AI models like BERT, GPT, and T5! In this in-depth tutorial, we’ll explore how the encoder processes inputs to capture meaningful patterns for tasks such as natural language processing (NLP) and machine translation. Whether you're an AI enthusiast, data scientist,...
Mastering Transformers: Understanding Residual Connections and Layer Normalization (Part 5) #ai
Переглядів 5021 день тому
#transformers #generativeai #llm #ai In this fifth episode of our Transformers series, we'll explore two essential components: residual connections and layer normalization. These techniques play a crucial role in improving the training and performance of transformer models. Join us as we break down these concepts and their applications. This video is perfect for anyone looking to understand the...
Mastering Transformers: A Clear Explanation of Self-Attention and Multi-Head Attention (Part 4) #ai
Переглядів 12321 день тому
#transformers #generativeai #llm #ai Confused by self-attention and multi-head attention? This video is for you! We're continuing our exploration of transformers, and in this episode, we'll provide a clear and concise explanation of these key components. Gain a deeper understanding of how transformers work and their applications. This video is perfect for anyone looking to understand the techni...
Introduction To Llama 3.2 | Finetuning Llama-3.2 Model Using Unsloth | Finetuning Using Unsloth
Переглядів 33128 днів тому
Llama 3.2 is a collection of large language models (LLMs) pre trained and fine-tuned in 1B and 3B sizes that are multilingual text only, and 11B and 90B sizes that take both text and image inputs and output text. In this comprehensive tutorial, learn how to fine-tune the LLaMA 3.1 3B model using Unsloth, a powerful and user-friendly tool for optimizing large language models (LLMs). Whether you'...
Embeddings & Positional Encoding in Transformers | Key Components of Transformers Simplified
Переглядів 52Місяць тому
#transformers #generativeai #llm #ai Unlock the secrets of Embeddings and Positional Encoding in Transformers with this easy-to-follow tutorial! In this video, we break down how embeddings work and why positional encoding is crucial for transformer models like BERT, GPT-3, and T5. Whether you're a beginner or looking to deepen your knowledge, this video offers a simplified approach to understan...
Introduction To Set Datatype | Set Datatype In Python | Python Simplified 2024 #set #sets
Переглядів 78Місяць тому
#pythoncourses #coding #pythonprogramming #pythontutorial #python3 #pythonforbeginners #sets Hello Viewers, In this video I have explained In detail about starting Python and how to learn in 2024. do check out the video completely. and do like share and subscribe to the channel. I have also created a BOOK regarding it. the book link is available below. Business email id- sktech.programming@gmai...
Transformers Architecture Explained | Key Components of Transformers Simplified #transformers
Переглядів 160Місяць тому
Welcome to Episode 2 of Transformers Simplified! 🚀 In this video, we dive deep into the architecture of transformers and break down the key components that make these models so powerful. From the encoder-decoder structure to self-attention mechanisms, you’ll gain a clear understanding of how transformers work behind the scenes. 🔍 In this video, you'll learn: 1. The core structure of transformer...
Introduction to Transformers | Transformers In NLP | Transformers Simplified #transformers
Переглядів 125Місяць тому
Welcome to the first video in our Transformers Simplified playlist! 🚀 In this episode, we break down the basics of transformers, the powerful architecture behind many state-of-the-art AI models like BERT, GPT, and more. Whether you're new to deep learning or looking to solidify your understanding, this introduction covers key concepts in a simple, digestible way. 🔍 What you'll learn: 1. What ar...
Python Simplified | Introduction To Dictionary Datatype | Dictionary Datatype In Python #dict
Переглядів 70Місяць тому
#pythoncourses #coding #pythonprogramming #pythontutorial #python3 #pythonforbeginners #dict #dictionary Hello Viewers, In this video I have explained In detail about starting Python and how to learn in 2024. do check out the video completely. and do like share and subscribe to the channel. I have also created a BOOK regarding it. the book link is available below. Business email id- sktech.prog...
Mastering RAG Pipelines with GitHub Models: A Step-by-Step Guide | Introduction To GitHub Models #ai
Переглядів 173Місяць тому
#AI #GitHubModels #RAGPipelines #MachineLearning #DataScience #AIGuide #techtutorial Unlock the power of Retrieval-Augmented Generation (RAG) in AI with this in-depth, hands-on guide! 🚀 In this video, we take you through a step-by-step process of mastering RAG pipelines using GitHub models, perfect for developers, AI enthusiasts, and data scientists looking to optimize their workflows. Learn ho...
Tuple Data Type In Python | What Are Tuples | Python Simplified | Learn Python 2024 #python #tuple
Переглядів 24Місяць тому
Tuple Data Type In Python | What Are Tuples | Python Simplified | Learn Python 2024 #python #tuple
List Data Type In Python And It's Operations | Python Simplified | Learn Python 2024 #python
Переглядів 109Місяць тому
List Data Type In Python And It's Operations | Python Simplified | Learn Python 2024 #python
Finetuning Llama-3.1 8b model Using Unsloth| Model Finetuning Using Unsloth
Переглядів 7952 місяці тому
Finetuning Llama-3.1 8b model Using Unsloth| Model Finetuning Using Unsloth
String Data Type In Python And It's Operations | Python Simplified | Learn Python 2024 #python
Переглядів 752 місяці тому
String Data Type In Python And It's Operations | Python Simplified | Learn Python 2024 #python
Roadmap To Become LLMOPS Engineer | LLMOPS Simplified | Detailed AiOP's Roadmap #llmops #geneai
Переглядів 2512 місяці тому
Roadmap To Become LLMOPS Engineer | LLMOPS Simplified | Detailed AiOP's Roadmap #llmops #geneai
What are Operators In Python | Types Of Operators In Python | Python Simplified #python3 #python
Переглядів 282 місяці тому
What are Operators In Python | Types Of Operators In Python | Python Simplified #python3 #python
Variables and Datatypes In Python | Learn Python In 2024 | Python Simplified #python3 #python
Переглядів 3562 місяці тому
Variables and Datatypes In Python | Learn Python In 2024 | Python Simplified #python3 #python
Python Programming Installation and Setup | Learn Python In 2024 | Install Python, Anaconda, Vscode
Переглядів 692 місяці тому
Python Programming Installation and Setup | Learn Python In 2024 | Install Python, Anaconda, Vscode
Application and Versatility Of Python | Learn Python In 2024 | Python Simplified #python #python3
Переглядів 462 місяці тому
Application and Versatility Of Python | Learn Python In 2024 | Python Simplified #python #python3
Introduction To Python Programming | Learn Python In 2024 | Python Simplified #python #python3
Переглядів 892 місяці тому
Introduction To Python Programming | Learn Python In 2024 | Python Simplified #python #python3
Meta Llama 3.1 405B Released! | Llama 3.1 better than GPT4 ?? OpenAI vs Meta's Llama 3.1 405B model
Переглядів 783 місяці тому
Meta Llama 3.1 405B Released! | Llama 3.1 better than GPT4 ?? OpenAI vs Meta's Llama 3.1 405B model
Python Roadmap for Beginners: Complete Series Roadmap and Index | Learn Python from Scratch #python
Переглядів 2463 місяці тому
Python Roadmap for Beginners: Complete Series Roadmap and Index | Learn Python from Scratch #python
The Power of Graph RAG Unleashed | GraphRAG End-to-End Implementation With @Microsoft Azure OpenAI
Переглядів 6 тис.3 місяці тому
The Power of Graph RAG Unleashed | GraphRAG End-to-End Implementation With @Microsoft Azure OpenAI
Develop Generative AI solutions Using Azure OpenAI Services Lab Solution Video #generativeai #azure
Переглядів 8853 місяці тому
Develop Generative AI solutions Using Azure OpenAI Services Lab Solution Video #generativeai #azure
Fundamentals of Responsible Generative AI Using Azure OpenAI Service #azureopenai #generativeai
Переглядів 1373 місяці тому
Fundamentals of Responsible Generative AI Using Azure OpenAI Service #azureopenai #generativeai
How Russia is trying to disrupt the 2024 Paris Olympic Games Using AI Report From Microsoft (MTAC)
Переглядів 374 місяці тому
How Russia is trying to disrupt the 2024 Paris Olympic Games Using AI Report From Microsoft (MTAC)
Retrieval Augmented Generation With Azure OpenAI Service | Generative Ai Using Azure OpenAI #azure
Переглядів 5184 місяці тому
Retrieval Augmented Generation With Azure OpenAI Service | Generative Ai Using Azure OpenAI #azure
Thank you very much for this explanation. Can you make more videos on the HybridRAG( combining the power of vectorDB and GraphDB) approaches.
The AI is so bad… I think it is very hilariously awful and can at times spread misleading information or whatever.
Sir please make a complete roadmap to master computer vision
Cloud for the win. No hassle of downloading it locally. thanks for the tutorial.
Yes cloud is easy to setup and use
Thnkuu sir for such detailed roadmap
Thanks for the lecture.I have used ollama pull llama3 in my environment .I have used this in langchain agent .My question is as response going to llm and coming from llm(through rest api), I want to see the how my input preprocessing in the model,how to do it because I am running on local server .There must be some way to get into modela nd see how it is working
sir the gguf model is not being download there are some issues can you help me ?
What is the issue. ??
Thank you for your work 👍
Can we deploy this online and make an api for it, for free?
You can write script to deploy yes it's possible
Andhra style biryani ☠️☠️
Yes, please do a Microsoft Applied skills: "Develop AI agents using Microsoft Azure OpenAI and Semantic Kernel. big thanks
Yes sure
See running a notebook is fine, do something new for others to gain....just a honest feedback but good explaination and work
Thanks for the feedback
bro i get this certificate free you didn't show here how give exam free
It's long back. Now that event is over
No comments, shared yet.
ua-cam.com/video/JnNCdEn0-4I/v-deo.html
How can i contact you
Linkedin - www.linkedin.com/in/sai-kumar-reddy-n-data-scientist?
You showed just text data. Does it also support csv data . e.g scenario which needs answering questions based on csv and pdf data both?
Yes but that code and execution is different. And approach is also different
@@SAIKUMARREDDYN Thanks so much is there any link / video i can follow for structured data like csv files in microsoft graph approach ?
Can you explain Multimodal GraphRAG? If we modify this code to include images, what necessary steps need to be taken??
Yes definitely will check and come up with it soon
Really well explained
I am getting this error while querying , can anyone help with this usage: python -m graphrag.query [-h] [--config CONFIG] [--data DATA] [--root ROOT] --method {local,global} [--community_level COMMUNITY_LEVEL] [--response_type RESPONSE_TYPE] [--streaming] query python -m graphrag.query: error: argument --method: invalid SearchType value: 'local/global'
You need to use either local or global not both search check the GitHub readme for more detail instructions
thanks
can you say which region has free arm instances because hyderabad and Mumbai region are out of stock
You need to verify payment as well. It will mostly be available in all regions
Hello MR Sai Kumar, while inserting in the document , it is throwing an error such as bad authentication indicating that, my credentials might be wrong while all the credentials are corrected when i double checked, can u please help on this one?
Please check code once or share GitHub link of code file to check further and make sure to remove your url. Before pushing it to GitHub
session was nice but ca you make video ongraph rag using open source llms or groq api key
Sure will check and do that
thank you sir
Cool, this channel is really great. I have created embeddings on mongoDB to perform vector search, but to use it, we have to assign limit inside the vector search aggregation pipeline which always returns me the non-essential data. If the limit is too high, and if it is low, it will definitely miss some of the important data. I can't really fix this limit to get a particular number of matches because of the backend complexity. Can you please suggest me some alternatives or any solution to get the result which matches the user query. I also can't rely on the vector search score because they all are so close depending on the user query.
tqs for this video sir i am searching FREE API for months tqs sir, while using the API key does we need to paste all the code you mentioned or save the API key in .env and when required we can use from os.env for the required tasks
You need to generate api key each time. And you already have sample code in nvidia website only how to use. It's easy like how we use openapi key almost same
kya yah hianime par lanch kara ja sakta hai
Sir does project IDX leverages the cloud GPU s
Mostly minimal gpus not advance ones
Oracle
wow! it's amazing Sai, so how about the newely release Microsoft Applied skills: "Develop AI agents using Microsoft Azure OpenAI and Semantic Kernel? I got stuck on task 2, could you please make a video on that? thanks
Sure please share link let me check
Hey bro on Microsoft website it's all in words ... where can i find videos to learn all these please help..thanx
I have created playlist already on those please check them
please make full playlist on this
Sure
@@SAIKUMARREDDYN Thanks
i haven't watched the vid yet, but i experimented w/ graphrag when it came out ~5 mo ago... and it didn't work (back then) ~90% of the time (well, my implementation at least) and it was sloooooooow AKA computationally expensive; then triplets (sci-phi triplex) came out - have you experimented with that? my findings are that it's super fast (well, compared to graphrag) an maybe about on par (i didn't do a deep-dive / exhaustive test yet). what's your thought on that?
ps "global" used to fail at ~90%, not local, w/ graphrag.
rl demo of matriarchy 🤣🤣🤣
wow best intro ever 🤣🤣🤣🤣💖💖
Hi bro any idea on how to embed existing documents in mongodb, i already have json data and wanted to do rag upon it, like how to bypass the loader part or how to load using json( tried that but not working)...
that's a bit different approch. i hope you already have embeddings of that input data you stored in mongodb. if no create embeddings and store it. then call your mongo cluster and configure for working. mongodb refer this doc - www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/
please create a video on transformers as well , Thanks in advance, your videos are very helpful.
Sure
Sai, Please share the whimsical link
whimsical.com/mlops-roadmap-UaAtBWznsuoiXuVMEnECTa
That was really helpful. Can you tell why are we using lancedb here? What information is being stored in it? How exactly do we use it during local search?
lancedb is not mentioned in my code or explained. i explained mostly about graphrag that's all. but LanceDB is a cutting-edge, serverless vector database designed for developers who need a scalable, efficient, and easy-to-manage database solution. It supports storage of actual data alongside embeddings and metadata, unlike most existing vector databases that store only embeddings and metadata separately. This allows for a more comprehensive data management experience.
What if you want to plug different types of existing neo4j graphdatabase instead of a sample text? I'd love to know how to give the llm access to the already existing nodes and edges
For now Microsoft has opensource this code. Let me try I am looking for it.
How to extract the context from where LLM is generating the answer as mentioned in each answer [Data: Entities(XY)]
it shows the capability but not the usability in the production level. for instanse I do not want to reindex every documents each time there is an addition or a document is updated.
10 minutes for a response ?
It depends on your laptop GPU.
Thank you very much for the live demo.
Boss you have overloaded my brain. Will have to make graph rag of all your vids. Thank you for the basic understanding. If based in mumbai i would sure af like tuitions in pythong. Language. Want to learn how to speak in pythoniese. Basically.
😅🤣 i am based out of Bengaluru. but yes feel free to message me on LinkedIn. i am open to discuss this further👍
I am waiting sir when will you start python lecture. you have described road map of python amazing sir
Will release tomorrow 🤩.
what is the cost incurred for indexing... Any details or reference on that?
Cost might be approximately 1$. That's what I got on my bill cycle. And it's recommended to terminate azure openai once usage is done.
0 (only cost of electricity) if you run inference locally
Sir , better to make a roadmap of mlops similar to krish naik data science roadmap , with resources .
Joining in the journey of yours, Day 1 video completed.
What are the four files (claim_extraction, community_report, entity_extraction, summarize_description) within the Prompts folder for?
They are the prompt files which guide the llm model to create the graph representation of the text that you upload. In short, you're using prompt engineering technique on the llm model that you're using to create a graphical representation of the text file.
@@SAIKUMARREDDYN Those are optional to edit right. Do we need to edit all those files for every input file we test? Also, during initial test run, I didn't comment those files reference in settings.yml. (In settings.yml there were references to these four files). So for a different input, we will be having different prompt files. Won't that cause issue?