Rohan-Paul-AI
Rohan-Paul-AI
  • 435
  • 673 263
Intelligent LLM routing tool to choose the best Model for you and save you a ton of Money 💵
🔗 Sign up here to get your free NotDiamond API - www.notdiamond.ai/features
🔗 Official NotDiamond Doc - notdiamond.readme.io/docs/what-is-not-diamond
🔗 An open-sourced AI chat app that utilizes advanced LLM model routing powered by Not Diamond -github.com/mckaywrigley/ai-router-chat
-----------------
🐦 Connect with me on TWITTER: rohanpaul_ai
Hi, I am a Machine Learning Engineer | Kaggle Master. Connect with me on 🐦 TWITTER: rohanpaul_ai - for daily in-depth coverage of Large Language Model bits
----------------
You can find me here:
**********************************************
🐦 TWITTER: rohanpaul_ai
👨🏻‍💼 LINKEDIN: www.linkedin.com/in/rohan-paul-ai/
👨‍🔧 Kaggle: www.kaggle.com/paulrohan2020
👨‍💻 GITHUB: github.com/rohan-paul
🧑‍🦰 Facebook : rohan.paul.562/
📸 Instagram: rohan_paul_2020
**********************************************
Other Playlist you might like 👇
🟠 MachineLearning & DeepLearning Concepts & interview Question Playlist - bit.ly/380eYDj
🟠 ComputerVision / DeepLearning Algorithms Implementation Playlist - bit.ly/36jEvpI
🟠 DataScience | MachineLearning Projects Implementation Playlist - bit.ly/39MEigt
🟠 Natural Language Processing Playlist : bit.ly/3P6r2CL
----------------------
#LLM #Largelanguagemodels #Llama3 #LLMfinetuning #opensource #NLP #ArtificialIntelligence #datascience #textprocessing #deeplearning #deeplearningai #100daysofmlcode #neuralnetworks #datascience #generativeai #generativemodels #OpenAI #GPT #GPT3 #GPT4 #chatgpt #genai
มุมมอง: 213

วีดีโอ

EyeLevel's GroundX innovative RAG platform transforming document processing and retrieval with LLMs13:17EyeLevel's GroundX innovative RAG platform transforming document processing and retrieval with LLMs
EyeLevel's GroundX innovative RAG platform transforming document processing and retrieval with LLMs
มุมมอง 9028 วันที่ผ่านมา
👉 Read the original blog post with much more details here - www.eyelevel.ai/post/most-accurate-rag 👉 Try EyeLevel's GroundX APIs here - www.groundx.ai/ 👉 Process your documents through their x-ray eyelevel.ai/xray 🐦 Connect with me on TWITTER: rohanpaul_ai Checkout the MASSIVELY UPGRADED 2nd Edition of my Book (with 1300 pages of Dense Python Knowledge) 🐍🔥 Covering 350 Python 🐍 Core...
How to make your LLMs apps ingest real-time data and index it on the fly at scale.34:00How to make your LLMs apps ingest real-time data and index it on the fly at scale.
How to make your LLMs apps ingest real-time data and index it on the fly at scale.
มุมมอง 231หลายเดือนก่อน
🐦 Connect with me on TWITTER: rohanpaul_ai 👉 Indexify official site - getindexify.ai/ 👉 Github - github.com/tensorlakeai/indexify 👉 Official documentation - docs.getindexify.ai 👉 Read their announcement blog - medium.com/tensorlake-ai/announcing-indexify-a36f69967884 Checkout the MASSIVELY UPGRADED 2nd Edition of my Book (with 1300 pages of Dense Python Knowledge) 🐍🔥 Covering 350 Py...
R2R (RAG to Riches) | Out-of-the box RAG Engine with Python & Javascript SDKs | Local Model Support26:03R2R (RAG to Riches) | Out-of-the box RAG Engine with Python & Javascript SDKs | Local Model Support
R2R (RAG to Riches) | Out-of-the box RAG Engine with Python & Javascript SDKs | Local Model Support
มุมมอง 1.4Kหลายเดือนก่อน
👉 R2R Official Doc - r2r-docs.sciphi.ai/introduction 👉 Github repo of R2R - github.com/SciPhi-AI/R2R 🐦 Connect with me on TWITTER: rohanpaul_ai Checkout the MASSIVELY UPGRADED 2nd Edition of my Book (with 1300 pages of Dense Python Knowledge) 🐍🔥 Covering 350 Python 🐍 Core concepts ( 1300 pages ) 🚀 🟠 Book Link - rohanpaul.gumroad.com/l/python-core-with-under-the-hood-explanations Hi,...
Build Mixture of Agents (MoA) & RAG with Open Source Models in Minutes with JamAI Base44:01Build Mixture of Agents (MoA) & RAG with Open Source Models in Minutes with JamAI Base
Build Mixture of Agents (MoA) & RAG with Open Source Models in Minutes with JamAI Base
มุมมอง 760หลายเดือนก่อน
🔗 Try out JamBase AI here - cloud.jamaibase.com/ 🔗 Github repo - github.com/EmbeddedLLM/JamAIBase @5:33 Build a Mixture of Agents (MoA) system without writing a single line of code with JamAI Base @12:51 Build a RAG system to perform Due Diligence on Arm Holdings Limited's F-1 filing for their upcoming IPO ✨ Introducing you to JamAI Base, I just found out about this platform, where you can buil...
Fundamentals of LLM Finetuning | Launch latest Llama-3.1 finetuning with MonsterAPI's in minutes46:37Fundamentals of LLM Finetuning | Launch latest Llama-3.1 finetuning with MonsterAPI's in minutes
Fundamentals of LLM Finetuning | Launch latest Llama-3.1 finetuning with MonsterAPI's in minutes
มุมมอง 505หลายเดือนก่อน
Below are all the important links. 👉 MonsterAPI Official site: monsterapi.ai/signup?ref=rohan 👉 Google colab for LLM Finetuning with MonsterTuner API - colab.research.google.com/drive/1RLGJJ6u-crgP_fO1V2VKAZPpDCJ95lCp?usp=sharing&ref=blog.monsterapi.ai 👉 MonsterGPT official guideline: monsterapi.ai/gpt 👉 blog.monsterapi.ai/blogs/finetuning-a-large-language-model/ 👉 Discord (MonsterAPIs) : disco...
Inferencing Llama 3.1 405B right now for FREE on NVIDIA NIM0:47Inferencing Llama 3.1 405B right now for FREE on NVIDIA NIM
Inferencing Llama 3.1 405B right now for FREE on NVIDIA NIM
มุมมอง 480หลายเดือนก่อน
🔴 Check out NVIDIA NIM here - nvda.ws/3Vg4vbu 🐦 Connect with me on TWITTER: rohanpaul_ai 📌 NVIDIA NIMs is an inference microservices that provide models as optimized containers - to deploy on clouds, data centers or workstations, giving them the ability to easily build generative AI applications for copilots, chatbots and more, in minutes rather than weeks. 📌 Maximizes infrastructur...
Lllama-3 Inference | SSH into a Cloud GPU - with Hyperstack by Nexgen Cloud43:03Lllama-3 Inference | SSH into a Cloud GPU - with Hyperstack by Nexgen Cloud
Lllama-3 Inference | SSH into a Cloud GPU - with Hyperstack by Nexgen Cloud
มุมมอง 124หลายเดือนก่อน
👨‍🔧 Over the past months quite a few incredible models were released like Llama-3 70B, DeepSeek Coder V2, Mistral CodeStral and in terms of param-sizes all of them are MASSIVE. So given their huge sizes, for inference or finetuning you definitely going to need cloud based GPU. 📌 In this video I will discuss a brilliant cloud-GPU provider, Hyperstack, that allows you to own, operate, and optimiz...
robocoder - AI Software Engineer from blackbox.ai 👨‍🔧 powered by the best of LLMs0:51robocoder - AI Software Engineer from blackbox.ai 👨‍🔧 powered by the best of LLMs
robocoder - AI Software Engineer from blackbox.ai 👨‍🔧 powered by the best of LLMs
มุมมอง 374หลายเดือนก่อน
Checout robocoder here - www.robocoders.ai/ Create beautiful games robocoder from blackbox .ai - powered by some of the best LLMs. What sets Robocoder apart is its ability to handle both front-end and back-end coding and execution, including making 3rd party API calls. Available for all users, no waiting period. 🐦 Connect with me on TWITTER: rohanpaul_ai Checkout the MASSIVELY UPGRA...
Blackbox.ai vs ChatGPT-4 vs Anthropic Claude 3.5 Sonnet - Executing 3rd party API Calls5:12Blackbox.ai vs ChatGPT-4 vs Anthropic Claude 3.5 Sonnet - Executing 3rd party API Calls
Blackbox.ai vs ChatGPT-4 vs Anthropic Claude 3.5 Sonnet - Executing 3rd party API Calls
มุมมอง 381หลายเดือนก่อน
Blackbox.ai vs ChatGPT-4 vs Anthropic Claude 3.5 Sonnet - Executing 3rd party API Calls. What sets Blackbox.ai apart is its ability to execute a real-time third-party API call, which you can not do with ChatGPT4 or Anthropic Claude. 🐦 Connect with me on TWITTER: rohanpaul_ai Checkout the MASSIVELY UPGRADED 2nd Edition of my Book (with 1300 pages of Dense Python Knowledge) 🐍🔥 Coverin...
Robocoder from blackbox.ai | AI Software Engineer ( takes care of both frontend & backend coding)5:53Robocoder from blackbox.ai | AI Software Engineer ( takes care of both frontend & backend coding)
Robocoder from blackbox.ai | AI Software Engineer ( takes care of both frontend & backend coding)
มุมมอง 721หลายเดือนก่อน
🔴 Checkout blackbox.ai here - www.blackbox.ai/ The robocoder is accessible to all - no waiting period. But what really sets Robocoder apart is its ability to handle both front-end and back-end development, including making API calls to third-party services. 📌 Coding copilot with Real-Time Web Search with Blackbox.ai and it is FREE 🔥 📌 Blackbox.ai: Your Agentic Copilot for Analytics and Machine ...
Blacbox.ai - the LLM-based coding copilot for your entire software development cycle 👨‍🔧24:16Blacbox.ai - the LLM-based coding copilot for your entire software development cycle 👨‍🔧
Blacbox.ai - the LLM-based coding copilot for your entire software development cycle 👨‍🔧
มุมมอง 359หลายเดือนก่อน
Checkout - www.blackbox.ai/ 📌 Coding copilot with Real-Time Web Search with Blackbox.ai and it is FREE 🔥 📌 Blackbox.ai: Your Agentic Copilot for Analytics and Machine Learning 📌 Code Documentation with AI-Powered Comments and Docstrings is a breeze with Blackbox .ai 👨‍🔧 📌 Supercharge Your Git Workflow: Blackbox .ai's Automatic Commit Messages, Saving developers tons of time and headaches 🐦 Conn...
NVIDIA AI Workbench: Easily Scale your AI Application Development | Step by Step Guide39:59NVIDIA AI Workbench: Easily Scale your AI Application Development | Step by Step Guide
NVIDIA AI Workbench: Easily Scale your AI Application Development | Step by Step Guide
มุมมอง 7812 หลายเดือนก่อน
With NVIDIA AI Workbench, developers and data scientists have the flexibility to start an AI or ML project locally on a PC or workstation and then migrate- it anywhere. Projects can be pushed out to a data center, public cloud, or NVIDIA DGX Cloud, or moved to a local RTX PC or workstation for inference and customization. Available for FREE in Ubuntu (22.04 and 24.04), Windows and Mac. 🚀 Boosts...
Build powerful Agents and connect with external tools by drag and drop - with Dify.ai 🔥40:30Build powerful Agents and connect with external tools by drag and drop - with Dify.ai 🔥
Build powerful Agents and connect with external tools by drag and drop - with Dify.ai 🔥
มุมมอง 1.2K2 หลายเดือนก่อน
👉 Checkout Dify here - dify.ai/?@RohanPaul-AI& 👉 Documentation page of Dify - docs.dify.ai/ 👉 Twitter Handle of Dify @dify_ai - x.com/dify_ai Hi, I am a Machine Learning Engineer | Kaggle Master. Connect with me on 🐦 TWITTER: rohanpaul_ai - for daily in-depth coverage of Large Language Model bits You can find me here: 🐦 TWITTER: rohanpaul_ai 👨🏻‍💼 LINKEDIN: www.linkedin.c...
blackbox-ai | Powerful-Alternative to Github-Copilot | Code 10X Faster 🔥9:17blackbox-ai | Powerful-Alternative to Github-Copilot | Code 10X Faster 🔥
blackbox-ai | Powerful-Alternative to Github-Copilot | Code 10X Faster 🔥
มุมมอง 5483 หลายเดือนก่อน
Try here: blackbox.ai With 2.4mn download (of blackbox.ai's vscode extension), its literally used by millions of Front-end, backend, data scientists and machine learning engineers to speed up their workflow to produce code 10X faster. ✨ 🐦 Connect with me on TWITTER: rohanpaul_ai Hi, I am a Machine Learning Engineer | Kaggle Master. Connect with me on 🐦 TWITTER: rohanpaul...
Deploy finetuned LLMs with Public API endpoints from ChatGPT using CustomGPT | No code to write13:35Deploy finetuned LLMs with Public API endpoints from ChatGPT using CustomGPT | No code to write
Deploy finetuned LLMs with Public API endpoints from ChatGPT using CustomGPT | No code to write
มุมมอง 2023 หลายเดือนก่อน
Deploy finetuned LLMs with Public API endpoints from ChatGPT using CustomGPT | No code to write
World's first finetuning and deployment agent - Finetune & Deploy LLMs by only chatting from ChatGPT12:25World's first finetuning and deployment agent - Finetune & Deploy LLMs by only chatting from ChatGPT
World's first finetuning and deployment agent - Finetune & Deploy LLMs by only chatting from ChatGPT
มุมมอง 2593 หลายเดือนก่อน
World's first finetuning and deployment agent - Finetune & Deploy LLMs by only chatting from ChatGPT
Finetune Llama-3-8B with unsloth 4bit quantized with ORPO17:45Finetune Llama-3-8B with unsloth 4bit quantized with ORPO
Finetune Llama-3-8B with unsloth 4bit quantized with ORPO
มุมมอง 7633 หลายเดือนก่อน
Finetune Llama-3-8B with unsloth 4bit quantized with ORPO
Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models | New LLMs Paper8:48Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models | New LLMs Paper
Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models | New LLMs Paper
มุมมอง 2453 หลายเดือนก่อน
Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models | New LLMs Paper
Run Mixtral 8x7B-on a free-tier Google Colab with AQLM-2bit quantization4:59Run Mixtral 8x7B-on a free-tier Google Colab with AQLM-2bit quantization
Run Mixtral 8x7B-on a free-tier Google Colab with AQLM-2bit quantization
มุมมอง 2833 หลายเดือนก่อน
Run Mixtral 8x7B-on a free-tier Google Colab with AQLM-2bit quantization
GPT-4 O is REAL BIG DEAL6:18GPT-4 O is REAL BIG DEAL
GPT-4 O is REAL BIG DEAL
มุมมอง 4153 หลายเดือนก่อน
GPT-4 O is REAL BIG DEAL
LYZR - Low-code LLM Agent with pre-built RAG pipelines & LangChain alternative30:29LYZR - Low-code LLM Agent with pre-built RAG pipelines & LangChain alternative
LYZR - Low-code LLM Agent with pre-built RAG pipelines & LangChain alternative
มุมมอง 3773 หลายเดือนก่อน
LYZR - Low-code LLM Agent with pre-built RAG pipelines & LangChain alternative
Llama 3 degrades much more than Llama 2 when quantized 🤔 | New LLM Paper Finds out7:47Llama 3 degrades much more than Llama 2 when quantized 🤔 | New LLM Paper Finds out
Llama 3 degrades much more than Llama 2 when quantized 🤔 | New LLM Paper Finds out
มุมมอง 4743 หลายเดือนก่อน
Llama 3 degrades much more than Llama 2 when quantized 🤔 | New LLM Paper Finds out
Catastrophic Forgetting can NOT be avoided in Finetuned LLMs | New LLMs Paper6:21Catastrophic Forgetting can NOT be avoided in Finetuned LLMs | New LLMs Paper
Catastrophic Forgetting can NOT be avoided in Finetuned LLMs | New LLMs Paper
มุมมอง 4363 หลายเดือนก่อน
Catastrophic Forgetting can NOT be avoided in Finetuned LLMs | New LLMs Paper
Kolmogorov-Arnold Networks VS Regular Deep Learning | New Large Language Models (LLMs) Paper14:55Kolmogorov-Arnold Networks VS Regular Deep Learning | New Large Language Models (LLMs) Paper
Kolmogorov-Arnold Networks VS Regular Deep Learning | New Large Language Models (LLMs) Paper
มุมมอง 3.1K4 หลายเดือนก่อน
Kolmogorov-Arnold Networks VS Regular Deep Learning | New Large Language Models (LLMs) Paper
OpenAI-Assistant-API13:12OpenAI-Assistant-API
OpenAI-Assistant-API
มุมมอง 1384 หลายเดือนก่อน
OpenAI-Assistant-API
vLLM and PagedAttention is the best for fast Large Language Models (LLMs) inferencey | Lets see WHY5:50vLLM and PagedAttention is the best for fast Large Language Models (LLMs) inferencey | Lets see WHY
vLLM and PagedAttention is the best for fast Large Language Models (LLMs) inferencey | Lets see WHY
มุมมอง 9724 หลายเดือนก่อน
vLLM and PagedAttention is the best for fast Large Language Models (LLMs) inferencey | Lets see WHY
Deploy Llama-3-8B with vLLM | no need to write any code | Deploy directly from ChatGPT36:26Deploy Llama-3-8B with vLLM | no need to write any code | Deploy directly from ChatGPT
Deploy Llama-3-8B with vLLM | no need to write any code | Deploy directly from ChatGPT
มุมมอง 1.5K4 หลายเดือนก่อน
Deploy Llama-3-8B with vLLM | no need to write any code | Deploy directly from ChatGPT
Run 70Bn Llama 3 Inference on a Single 4GB GPU8:18Run 70Bn Llama 3 Inference on a Single 4GB GPU
Run 70Bn Llama 3 Inference on a Single 4GB GPU
มุมมอง 13K4 หลายเดือนก่อน
Run 70Bn Llama 3 Inference on a Single 4GB GPU
Llama-3 Finetuning on custom dataset with unsloth and QLORA30:01Llama-3 Finetuning on custom dataset with unsloth and QLORA
Llama-3 Finetuning on custom dataset with unsloth and QLORA
มุมมอง 4.6K4 หลายเดือนก่อน
Llama-3 Finetuning on custom dataset with unsloth and QLORA