Channel Avatar

Rithesh Sreenivasan @UCPAfv1GeraR1WM0608He6ow@youtube.com

14K subscribers - no pronouns :c

Educational videos on Generative Artificial Intelligence, Ma


16:00
Text-to-SQL using GPT-4o as LLM , SQLite DB Colab Python DemoπŸ”₯πŸ”₯
08:16
Archetype AI Physical AI Model NewtonπŸ”₯πŸ”₯
08:58
NVIDIA Nemotron 70B LLM πŸ’ͺ than Claude Sonnet 3.5, GPT-4o πŸ”₯πŸ”₯
10:07
Open AI o1 (πŸ“) Smartest AI Ever? First Look πŸ”₯πŸ”₯
08:37
Run Pixtral 12B Multimodal AI from Mistral on ColabπŸ”₯πŸ”₯
12:20
New Meta SAM 2 CV Model πŸ”₯πŸ”₯ Segment Anything Model for videos and images Demo First Look
11:38
Meta Llama 3.1 405 B πŸ”₯πŸ”₯ – Free Testing on Groq , Meta.AI First Look
11:00
Claude 3.5 Sonnet + Artifacts πŸ”₯πŸ”₯ – Testing Vision Capabilities Screenshot To Code
04:59
Anthropic Claude 3.5 Sonnet MLM+ Artifacts πŸ”₯πŸ”₯ -Create a blog within minutes
09:27
Google Gemma 2 27B and 9B LLM 27B close to LLAMA-3 70B Open Access Lightweight
11:10
πŸ”₯πŸ”₯ Microsoft Florence-2 Small Powerful Vision Foundation Model OCR, Caption, Object Detection 770 M
13:25
Microsoft Phi-3-Vision Powerful Small Multimodal Model Inference Walkthrough Colab Demo OCR
10:13
How to choose LLM inference backend? Benchmarking LLM Inference Backends from BentoML Engineering
10:52
A GPT-4V Level Multimodal LLM on Your Phone ??? MiniCPM-Llama3-V-2_5
10:40
GPT-4o INSANE CAPABILITIES COMPREHENSIVE PRACTICAL USE CASES DEMO #openai
05:29
Google DeepMind’s Project Astra – Future of Helpful AI Assistants Multimodal Realtime
11:28
META LLAMA 3 70B LLM – Zero Shot Aspect Based Sentiment Analysis Fast response Groq Collab Demo
13:53
META LLAMA 3 8B INSTRUCT LLM – How to Create Medical Chatbot with LlamaIndex FastEmbed Colab Demo
05:44
Reduce GPT-4 costs by 50% using BATCH API endpoint for asynchronous batch processing
10:46
Trying out Mixtral 8x22B MoE fine tuned Zephyr 141B-A35B Powerful Open source LLM
06:02
Grok 1.5 Vision Amazing Performance Better than GPT-4, Claude and Gemini 1.5?
08:51
Create a Python Coding Assistant with Google CodeGemma LLM Colab Tutorial #genai
04:11
MIXTRAL 8x22 B MOE LLM – ALL WE KNOW NEW MISTRAL AI OPENWEIGHTS NEW RELEASE
06:23
Google Introduces CodeGemma and RecurrentGemma LLMs πŸ”₯πŸ”₯πŸ”₯πŸ”₯ along with Gemma 1.1 LLM Open Models
06:36
AUTOCODEROVER AI SOFTWARE ENGINEER BETTER THAN SWE-AGENT AND DEVIN OPEN SOURCE
17:31
TOOL USE ( FUNCTION CALLING) πŸ”₯πŸ”₯ With Anthropic CLAUDE 3 API – A Step by Step Tutorial
08:03
RAG KING COHERE COMMAND R+ LLM πŸ”₯πŸ”₯ MULTILINGUAL MULTI STEP TOOL USE HIGH PERFORMANCE
05:39
New OPEN SOURCE AI SOFTWARE ENGINEER Agent SWE-AGENT better than Devin
15:47
How EdTech companies are fooling you with super expensive AI ML DS courses ? Scam
08:29
Jamba First Production Grade MAMBA LLM SSM-Transformer LLM MAMBA + Transformers + MoE
11:49
What is Matryoshka Embedding Models ? Similar accuracy with a smaller embedding size, speedups
10:15
Google Gemini 1.5 Pro Use Case Auto Question Answer , Topics , Chapter Generation from Video
05:24
Dangers of using LLM/V-LLM for medical image interpretation Feat Claude
08:41
Bye Open AI Sora Microsoft Mora Video Generation AI is here , Open source multi-agent framework
06:57
NVIDIA Generative AI Courses Free and Paid
05:39
Microsoft Generative AI for Beginners ( Version 2 ) - A Course
13:52
Cohere Embed v3 int8 & binary Embeddings 4X and 32X memory reduction 40x faster search
08:54
Bye Bye Devin Hello Microsoft AutoDev AI SWE
09:58
All about NVDIA Blackwell GPUs and GB200 NVL72 exascale computer
10:36
🦍 RAFT : Adapting Language Model to Domain Specific RAG Paper Discussion
04:27
Open Release of Grok-1 Implications 314 billion parameter Mixture-of-Experts LLM
12:02
Cohere Command-R High Performance Strong RAG LLM Demo
07:44
Devin First Fully autonomous AI software engineer Hype?? Marketing?? Cognition Labs
17:19
Testing out Google Gemini 1.5 Mutimodal LLM Google AI Studio
06:03
Anthropic Prompts Library Prompt Templates for Claude LLMs
13:25
Inflection 2.5 LLM : meet the world's best personal AI , Pi Upgraded Personal Safe Emphatic AI
09:51
Stable Diffusion 3 Text to Image AI Better than DALLΒ·E 3 , Midjourney v6 , and Ideogram v1
08:38
Can AI Replace Front End Engineering ? Design2Code Discussion
10:46
Newest Smartest AI Claude 3 beats GPT-4 Testing Claude 3 with Vision Anthropic vs Open AI
11:40
Kalaido.ai the Text-to-Image generator by Fractal Indian Foundational Model for Text to Image
03:39
Need Mentorship Guidance on Ml NLP Gen AI ? Having Queries? Meet with me 1:1 on Topmate
13:45
The Era of 1-bit LLMs BitNet b1.58 No Floating point operations for LLM
06:17
Mistral AI Mistral Large LLM Closer, Cheaper than GPT-4 Microsoft Azure Availability
11:33
Create Medical Chatbot with Google Gemma 7B LLM LlamaIndex Colab Demo Qdrant FastEmbed Gradio
05:54
Groq Labs LPU ( Language Processing Unit ) Chip Insane LLM Inference Speed
08:19
Google Gemma state-of-the-art open 2B and 7B LLM Quick look
11:04
RAG Vs Fine-Tuning Vs Both for LLM performance When to use which
07:12
Google Gemini 1.5 128K context Multimodal AI Is it impressive?
06:01
OpenAI Sora Mindblowing Text to Video AI Hype?
06:24
Cohere For AI Launches Aya, a LLM Covering More Than 100 Languages Open source Multilingual Dataset