- 289
- 1 421 016
AI Anytime
India
Registrace 31. 12. 2022
Welcome to AI Anytime, your source for the latest and greatest in Generative AI and ML. From tutorials to expert interviews, I cover it all. Subscribe for cutting-edge content on LLMs, Deep Learning, NLP, etc. Join us on this journey of AI and ML.
Synthetic Data Generation using LLM: Crash Course for Beginners
Check out this new video on "Synthetic Data Generation using LLM: Crash Course for Beginners." In this video, I cover the basics of synthetic data generation, explore different types, and introduce the tools and libraries you can use. I break down complex concepts into easy-to-understand segments, making it perfect for beginners.
Don't forget to like, comment, and subscribe for more insightful content on GenAI and ML.
GitHub: github.com/AIAnytime/Synthetic-Data-Generation-using-LLM
Join this channel to get access to perks:
czcams.com/channels/-zVytOQB62OwMhKRi0TDvg.htmljoin
To further support the channel, you can contribute via the following methods:
Bitcoin Address: 32zhmo5T9jvu8gJDGW3LTuKBM1KPMHoCsW
UPI: sonu1000raw@ybl
#ai #data #llm
Don't forget to like, comment, and subscribe for more insightful content on GenAI and ML.
GitHub: github.com/AIAnytime/Synthetic-Data-Generation-using-LLM
Join this channel to get access to perks:
czcams.com/channels/-zVytOQB62OwMhKRi0TDvg.htmljoin
To further support the channel, you can contribute via the following methods:
Bitcoin Address: 32zhmo5T9jvu8gJDGW3LTuKBM1KPMHoCsW
UPI: sonu1000raw@ybl
#ai #data #llm
zhlédnutí: 968
Video
Fine-Tuning with ReFT: Create an Emoji LLM for Medical Diagnosis
zhlédnutí 729Před 4 hodinami
Hey everyone! In this tutorial, I'll walk you through an exciting new fine-tuning method called ReFT (representation fine-tuning) using the powerful pyreft library. 🌟 Discover how you can fine-tune pretrained language models with fewer parameters and achieve potentially better performance. We'll dive into the process of creating an emoji LLM (Language Model) tailored for medical diagnosis quest...
Create Realistic Talking AI Agent with D-ID, UneeQ, and Azure AI
zhlédnutí 2,4KPřed 14 hodinami
Discover the power of Digital Humans and AI Agents in this video! Learn how to create AI Agent that can talk. Perfect for enhancing digital interactions, this tool allows you to build engaging conversational agents, virtual assistants, and interactive bots with ease. Dive into the technical workings, benefits, and diverse applications of this innovative technology. D-ID Here: www.d-id.com/ Unee...
Build a RAG Evaluation Tool and Python Library
zhlédnutí 1,7KPřed dnem
Welcome to my tutorial on how to build a Retrieval-Augmented Generation (RAG) Evaluation Tool and Python Library! In this video, I will guide you through the process of creating a comprehensive evaluation tool for RAG systems, complete with various metrics to assess the quality of generated text. What You'll Learn: ✅ Setting up the project structure ✅ Implementing evaluation metrics such as BLE...
LLMs Quantization Crash Course for Beginners
zhlédnutí 1,6KPřed dnem
Join me in this comprehensive tutorial where I dive deep into the world of quantization techniques for Large Language Models (LLMs). From basic concepts to advanced strategies, I cover everything you need to know to optimize your AI models for efficiency and performance. In this video, I: ✅ Explain the fundamentals of model quantization and its importance in the field of AI. ✅ Provide detailed ...
PaliGemma by Google: Inference and Fine Tuning of Vision Language Model
zhlédnutí 7KPřed 14 dny
In this video I'm diving deep into PaliGemma, a new vision language model by Google! PaliGemma can analyze images and text, making it super versatile for tasks like image captioning and question answering. I'll show you how to use this powerful tool and get the most out of it through fine-tuning. Don't forget to like and subscribe for more tech breakdowns! Notebook: github.com/AIAnytime/PaliGem...
Try GPT-4O (Omni Model) via API for Vision and Text
zhlédnutí 2,9KPřed 14 dny
Welcome to the latest tutorial on OpenAI's ground-breaking new model, GPT-4O! In this video, we delve into the advanced capabilities of GPT-4O, which stands for "omni," highlighting its multimodal features that integrate text, and vision. Released in May 2024, GPT-4O represents a significant leap forward in AI technology, enabling more versatile and sophisticated applications. We'll demonstrate...
Evaluate LLMs with Language Model Evaluation Harness
zhlédnutí 1,7KPřed 14 dny
In this tutorial, I delve into the intricacies of evaluating large language models (LLMs) using the versatile Evaluation Harness tool. Explore how to rigorously test LLMs across diverse datasets and benchmarks, including HellaSWAG, TruthfulQA, Winogrande, and more. This video features the LLaMA 3 model by Meta AI and demonstrates step-by-step how to conduct evaluations directly in a Colab noteb...
Build an End-to-End RAG API with AWS Bedrock & Azure OpenAI
zhlédnutí 3,8KPřed 21 dnem
In this tutorial, I show you how to build an end-to-end Retrieval-Augmented Generation (RAG) tool. I've used AWS Bedrock Service for the embedding models and knowledge base, Amazon OpenSearch Service for the vector database, and Azure OpenAI models for the language model. I'll walk you through setting up a Lambda function and creating a Python API using FastAPI to tie everything together into a...
Google’s Med-Gemini Multimodal LLM: The Best Medical AI Model
zhlédnutí 6KPřed 28 dny
Join me as I explore the ground-breaking advancements of Med-Gemini in the field of medical AI. In this video, I dive into some of the key findings and insights from the latest research, highlighting how Med-Gemini is setting new benchmarks in clinical reasoning, multimodal understanding, and long-context processing. Discover how these innovations could transform healthcare practices and enhanc...
Merge LLMs with No Code Mergekit GUI
zhlédnutí 2,5KPřed měsícem
In this video, I'm showing you how to easily merge Large Language Models (LLMs) using Mergkit and its no-code GUI. With these tools, you can merge LLMs in just 15 minutes, no coding required! I'll be demonstrating the process using the Llama3 base and Llama 38b instruction models. Want to see how to leverage the power of merged LLMs for your own projects? Then watch this video! If you found it ...
Quantize LLMs with AWQ: Faster and Smaller Llama 3
zhlédnutí 2,7KPřed měsícem
Quantize LLMs with AWQ: Faster and Smaller Llama 3
Estimate Memory Consumption of LLMs for Inference and Fine-Tuning
zhlédnutí 1,4KPřed měsícem
Estimate Memory Consumption of LLMs for Inference and Fine-Tuning
Phi-3 LLM by Microsoft: Real or Fake Results on Benchmarks?
zhlédnutí 3KPřed měsícem
Phi-3 LLM by Microsoft: Real or Fake Results on Benchmarks?
Fine Tune Multimodal LLM "Idefics 2" using QLoRA
zhlédnutí 1,8KPřed měsícem
Fine Tune Multimodal LLM "Idefics 2" using QLoRA
Mixtral 8x22b Instruct v0.1 MoE by Mistral AI
zhlédnutí 1,4KPřed měsícem
Mixtral 8x22b Instruct v0.1 MoE by Mistral AI
Build an On-Device RAG App using Open Source AI Stack
zhlédnutí 2,2KPřed měsícem
Build an On-Device RAG App using Open Source AI Stack
Jina Reader API: Build better AI Agents and RAG systems with Reader
zhlédnutí 2,2KPřed měsícem
Jina Reader API: Build better AI Agents and RAG systems with Reader
2D to 3D Object Reconstruction using Open Source AI
zhlédnutí 1,2KPřed měsícem
2D to 3D Object Reconstruction using Open Source AI
Audio Summarization App using Gemini 1.5 Multimodal AI
zhlédnutí 1,6KPřed měsícem
Audio Summarization App using Gemini 1.5 Multimodal AI
How to Calculate Software Carbon Intensity: A Quick Guide
zhlédnutí 345Před měsícem
How to Calculate Software Carbon Intensity: A Quick Guide
Vision Language Models: Leaderboards, Evaluation Benchmarks, and Learning
zhlédnutí 1,2KPřed měsícem
Vision Language Models: Leaderboards, Evaluation Benchmarks, and Learning
RecurrentGemma by Google: The best 2B LLM based on Griffin Architecture
zhlédnutí 2,4KPřed měsícem
RecurrentGemma by Google: The best 2B LLM based on Griffin Architecture
CodeGemma 2B & 7B LLM by Google: Open Source Coding LLMs
zhlédnutí 3,8KPřed měsícem
CodeGemma 2B & 7B LLM by Google: Open Source Coding LLMs
A Beginner's guide on Hyperparameters for LLM Fine Tuning
zhlédnutí 2,1KPřed měsícem
A Beginner's guide on Hyperparameters for LLM Fine Tuning
ORPO Explained: Superior LLM Alignment Technique vs. DPO/RLHF
zhlédnutí 1,6KPřed měsícem
ORPO Explained: Superior LLM Alignment Technique vs. DPO/RLHF
On-Device LLM Inference at 600 Tokens/Sec.: All Open Source
zhlédnutí 3,8KPřed 2 měsíci
On-Device LLM Inference at 600 Tokens/Sec.: All Open Source
Fast Fine Tuning and DPO Training of LLMs using Unsloth
zhlédnutí 2,3KPřed 2 měsíci
Fast Fine Tuning and DPO Training of LLMs using Unsloth
How do I fine tune llama 3 on a pdf?
nice! thank you for the video!
can i quantize llama 3 using it of t4 colab?
An awesome, excellent and clear explain on fine tunning! I think most of us will excited your next video on Unsloth!
Its perfect ❤️
Thank you for such an insightful, walkthrough!
climate_qa_chain = RetrievalQA.from_llm( llm=llm, retriever=get_context_storage().as_retriever(), prompt=prompt ) This code keeps giving me 429 error every time I try to use it with OpenAI. Can you let me know why this happens? I don't see it happening in the example video. Is there anything wrong that I am doing
Thank you soo much for making such an in depth video on this bro!!!
Wow I needed this. I swear I will pay for this once I get a job.
Hey bro, your video about finetuning IDEFICS2-8B was great. Appreciate that! Can you please show some insights over finetuning state of art multi-modal "OpenGVLab/InternVL-Chat-V1-5" using LoRa or QLoRA?
is there any way to use this on websites that you need to login to?
Only one question, how do you learn all these? I mean what is your approach - you go through the documentation, code and then learn? How you have byhearted all the code parameters ?
thanks for sharing
thanks for sharing
Thank you for your detailed explanation. Your classes are quite interesting and are building confidence to move further forward. I need some suggestions: I saw a medical chatbot using Llama 2 on a CPU machine, which was all open source. Similarly, I need to build an image-to-text multimodal model on a CPU using all open-source tools. Please provide your suggestions.
Thank you for your detailed explanation. Your classes are quite interesting and are building confidence to move further forward. I need some suggestions: I saw a medical chatbot using Llama 2 on a CPU machine, which was all open source. Similarly, I need to build an image-to-text multimodal model on a CPU using all open-source tools. Please provide your suggestions.
how to display chart and ask visualization questions?
Is ReFT performing better than LoRA? i mean the Accuracy mainly. Moreover, which is the best performing one among LoRA, DoRA and ReFT when we compare the Accuracy
Hello Sir, I have recently completed a project aimed at public welfare, and I am eager to make it open-source. I am reaching out to seek your guidance and want to disclose it to you Could you please let me know the best way to get in touch with you for further instructions? Thank you for your time and consideration.
please give complete code of this, your github repo has different code and doesnt work
hi, how to change the code, if I want to finetune it without quantization?
is it possible to train this model for grounding tasks? Such as object localization? Similar to what cogagent does but on my custom dataset
Hey I wanted to know that is the video of fine tuning mixtral MOE on pods removed?? Where can I access that onfoy
Great video ! Is there any opensource platform that does similar thing ?
@AI Anytime, Thank you for the great video and demo. Wanted to reiterate that the code for the Lambda function is missing on Github. Thanks.
is the site working for you guys?
Nice video. Very much informative
Glad you liked it
#CSK
CSK ❤️
thanks for this video, if there is any open source agent for digital avatar please do a video of that, TIA
Good video, thanks. Do you have any videos that show how to use a custom GPT as knowledge for D-ID agents? Meaning, do you know how to point the D-ID agent via API to an OpenAI GPT?
You need to do that programmatically. Have a look at their documentation.
@@AIAnytime thank you!
Excellent!.👍
Thank you! Cheers!
Like your videos when you actually hands on run through the processes like this. I think you underestimate the benefits... ie seeing the simple web tools you also use is a helpful thing.
why do you keep brining BJP? you should avoid politics when creating AI content, there is a bigger spectrum of people who follow you
It's not only BJP. It's both BJP and Congress. The use case is to build a poll agent.
Can you create a reactjs+ fastapi project without using openai, that is, using llm running locally (example: lama2)?
00:05 Develop a streamlit app to summarize CZcams videos using Haystack, Llama 2, Whisper, and open source models. 02:21 Using Haystack, Llama 2, Whisper, and Streamlit to build a CZcams video summarization app 06:31 Using Llama 2, Whisper, and Streamlit to build a CZcams video summarization app 08:37 Need to create custom scripts for llama CPP invocation layer and use PiTube library for video download. 12:33 Llama 2 model usage in Haystack for various use cases 14:43 Using local implementation of whisper transcriber and llama model in Haystack for summarization 18:32 Importing Llama, setting streamlit page configuration, and writing a function to download a CZcams video 20:19 Initializing the model and defining the invocation layer 24:06 Initializing the prompt node for using in Haystack 25:52 Using whispers for transcription with API key or local implementation 29:43 Setting up the pipeline for processing video data. 31:37 Styling the title with color, alignment, and HTML 36:25 Creating and using functions for downloading and processing CZcams videos 38:27 Setting up prompt node and distributing columns for video display and summarization 42:24 Building a CZcams video summarization app using pipeline and models 44:35 The speaker discusses using llm to retrieve relevant information from a CZcams video. 48:13 Encouraging audience engagement and communication. Crafted by Merlin AI.
Nice one
Thank you.
Welcome!
part 2
Hello sir, there is no next video on contextual compression, mitigate biases, remove redundant chunks, emsemble retriever(hybrid search) and other techniques to improve performance of rag chain. Please sir, can you share the video link. Thanks
Can you make a follow up video about this using their API into our RAG application? That would be amazing to do and a very unique video
Agree 💯
hi, I have been watching your videos for quite some time now. found them very useful and appreciate your effort and dedication to come with great videos. Just a question on GPU's. Now that most of the Laptops and desktops come with AMD Graphics card will they work well for Quantized models, your inputs please
Can one use this to query thousands of files?
Very nice video. Thank you!
This git repository has not been updated. Can you upload models, template files/folders
Your a god THX
Bro you look like Mr. Sundar Pichai
where is code link??
How can i generate Pictures with german words? Every picture i try to generate with gpt4o with correct German gives me pictures with a fantasy language ( no correct german). So will there bee soon the possibility for correct German in pictures with gtp4o or do I have to wait until gpt5?
Your video is very helpful! Could you please provide a technical architecture diagram for better insights and easier understanding? Sharing a link to the diagram would be greatly appreciated. Thank you!
this is awsome.can you suggest anything to extract audio or text from video?? any llm and its references code.and also do some analysis direct from video