- 2 683
- 1 646 520
Fahd Mirza
Australia
เข้าร่วมเมื่อ 7 ส.ค. 2020
Learn AI, Cloud, DevOps and Databases. Become a Better AI Cloud Engineer.
Stable Diffusion 3 Medium - Install Locally - Easiest Tutorial
This video is a step-by-step demo to install Stable Diffusion 3 Medium locally and generate high quality images for free with AI. Stable Diffusion 3 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model.
🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza
🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon:
bit.ly/fahd-mirza
Coupon code: FahdMirza
▶ Become a Patron 🔥 - patreon.com/FahdMirza
#comfyui #stablediffusion #stablediffusion3 #stablediffusion3medium
PLEASE FOLLOW ME:
▶ LinkedIn: www.linkedin.com/in/fahdmirza/
▶ TH-cam: www.youtube.com/@fahdmirza
▶ Blog: www.fahdmirza.com
RELATED VIDEOS:
▶ Resource huggingface.co/stabilityai/stable-diffusion-3-medium
All rights reserved © 2021 Fahd Mirza
🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza
🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon:
bit.ly/fahd-mirza
Coupon code: FahdMirza
▶ Become a Patron 🔥 - patreon.com/FahdMirza
#comfyui #stablediffusion #stablediffusion3 #stablediffusion3medium
PLEASE FOLLOW ME:
▶ LinkedIn: www.linkedin.com/in/fahdmirza/
▶ TH-cam: www.youtube.com/@fahdmirza
▶ Blog: www.fahdmirza.com
RELATED VIDEOS:
▶ Resource huggingface.co/stabilityai/stable-diffusion-3-medium
All rights reserved © 2021 Fahd Mirza
มุมมอง: 539
วีดีโอ
How To Install ComfyUI in Linux Windows and Mac
มุมมอง 879 ชั่วโมงที่ผ่านมา
This video is a step-by-step tutorial to install ComfyUI locally in Linux, Windows or any OS with GUI to run stable diffusion models. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #comfyui PLEASE FOLLOW ME: ▶ Lin...
Husky - A Unified Open-Source Language Agent for Multi-Step Reasoning
มุมมอง 33511 ชั่วโมงที่ผ่านมา
This video shows Husky which is a holistic, open-source language agent that learns to reason over a unified action space to address a diverse set of complex tasks involving numerical, tabular, and knowledge-based reasoning. Husky-v1 uses a code generator, a query generator and a math reasoner as expert models. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza ▶ Become a Patron 🔥 - p...
Atomic Agents - Building AI Agents Atomically
มุมมอง 50617 ชั่วโมงที่ผ่านมา
This video installs Atomic Agents framework which is designed to be modular, extensible, and easy to use. Components in the Atomic Agents Framework should always be as small and single-purpose as possible, similar to design system components in Atomic Design. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and...
RecurrentGemma 9B IT - Install and Test Locally
มุมมอง 19821 ชั่วโมงที่ผ่านมา
This video installs 9B instruction version of the RecurrentGemma model based on Griffin architecture. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #griffin #recurrentgemma#recurentgemma PLEASE FOLLOW ME: ▶ Linke...
Thread: AI-Powered Jupyter Notebook - Install Locally
มุมมอง 5692 ชั่วโมงที่ผ่านมา
This video installs Thread locally which is a Jupyter Notebook that combines the experience of OpenAI's code interpreter with the familiar development environment of a Python notebook. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - pat...
Apple’s on-Device New 3B Models With Adapters with AXLearn Framework
มุมมอง 1602 ชั่วโมงที่ผ่านมา
This video shares with you the latest innovation from Apple - Apple Intelligence! This personal intelligence system is integrated into iOS 18, iPadOS 18, and macOS Sequoia. It also sheds light on Apple's AXLearn framework. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #appleintellience #axlearn #apple3b #ios18 #ipados18 PLEASE FOLLOW M...
Install RecurrentGemma Model Locally - New Griffin Architecture
มุมมอง 1732 ชั่วโมงที่ผ่านมา
This video installs RecurrentGemma LLM which is a family of open language models built on a novel recurrent architecture developed at Google. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #griffin #recurrentgemma...
What is MatMul-free Language Modeling
มุมมอง 5372 ชั่วโมงที่ผ่านมา
This video shows the ground-breaking research about Matrix Multiplication (Matmul) that challenges the paradigm that MatMul operations are indispensable for building high-performing language models and paves the way for the development of more efficient and hardware-friendly architectures. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza ...
Whisper WebGPU - Multi-lingual AI Transcription Locally in Browser Locally
มุมมอง 1K2 ชั่วโมงที่ผ่านมา
This video is a step-by-step tutorial to install Whisper-WebGPU locally to do free local AI transcription in various languages like Urdu, Hindi, Arabic, Tamil and hundreds of others. Its ML-powered speech recognition directly in your browser. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/f...
Install Qwen-Agent with Ollama Locally to Create Agentic Apps for Function Calling
มุมมอง 9462 ชั่วโมงที่ผ่านมา
This video is a quick easy tutorial to install Qwen-Agent locally and create agentic applications with Qwen2 and Ollama for function calling and RAG. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #qwen #qwen2 #ol...
Run Qwen2 Model with Ollama Locally
มุมมอง 2312 ชั่วโมงที่ผ่านมา
This video is a quick easy tutorial to integrate Qwen2 model with Ollama locally. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #qwen #qwen2 #ollama PLEASE FOLLOW ME: ▶ LinkedIn: www.linkedin.com/in/fahdmirza/ ▶ ...
How to Fine-Tune an Audio AI Model in Any Language Locally
มุมมอง 1672 ชั่วโมงที่ผ่านมา
This video is a step-by-step tutorial to fine-tune or train your own AI model in any language on any custom dataset locally easily. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fahd-mirza Coupon code: FahdMirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #whisperai #urduaimodel #urdullm #...
A/B Testing of LLMs - Model Selection on Prompts and Params- Ollama Grid Search
มุมมอง 3094 ชั่วโมงที่ผ่านมา
This video demonstrates Ollama Grid Search tool and installs it locally to evaluate LLM models, prompts and model params. This project automates the process of selecting the best models, prompts, or inference parameters for a given use-case. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza 🔥 Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: bit.ly/fa...
Proofread with LLMs - Fixes All Errors with One Tap on Mobile Devices with Gboard
มุมมอง 1174 ชั่วโมงที่ผ่านมา
This video introduces Proofread which is a new Gboard feature powered by a server-side LLM in Gboard, enabling seamless sentence-level and paragraph level corrections with a single tap. 🔥 Buy Me a Coffee to support the channel: ko-fi.com/fahdmirza ▶ Become a Patron 🔥 - patreon.com/FahdMirza #gboard #llmproofread PLEASE FOLLOW ME: ▶ LinkedIn: www.linkedin.com/in/fahdmirza/ ▶ TH-cam: www.youtube....
Dolphin 2.9.2 Qwen2 7B - Better than Qwen2 - Install Locally
มุมมอง 5064 ชั่วโมงที่ผ่านมา
Dolphin 2.9.2 Qwen2 7B - Better than Qwen2 - Install Locally
Simplest Way to Download Models and Datasets from Hugging Face
มุมมอง 2994 ชั่วโมงที่ผ่านมา
Simplest Way to Download Models and Datasets from Hugging Face
Un-censored Qwen 2 Model (Abliterated) - Install Locally
มุมมอง 3004 ชั่วโมงที่ผ่านมา
Un-censored Qwen 2 Model (Abliterated) - Install Locally
Llama Zip - An LLM Powered Compression Tool
มุมมอง 2437 ชั่วโมงที่ผ่านมา
Llama Zip - An LLM Powered Compression Tool
How to Build Multi-Agent AI Application with AutoGen
มุมมอง 4667 ชั่วโมงที่ผ่านมา
How to Build Multi-Agent AI Application with AutoGen
Jina Clip - Multi-modal Embedding Model - Install Locally
มุมมอง 2007 ชั่วโมงที่ผ่านมา
Jina Clip - Multi-modal Embedding Model - Install Locally
Install GeM2 Llamion-14B LongChat Locally - Llamafied Orion
มุมมอง 1527 ชั่วโมงที่ผ่านมา
Install GeM2 Llamion-14B LongChat Locally - Llamafied Orion
Install LLMware Locally - RAG Pipeline on CPU
มุมมอง 4527 ชั่วโมงที่ผ่านมา
Install LLMware Locally - RAG Pipeline on CPU
Install Mobius AI Model Locally - High Quality Text to Image
มุมมอง 4497 ชั่วโมงที่ผ่านมา
Install Mobius AI Model Locally - High Quality Text to Image
Fine-Tune LLM in VS Code AI Toolkit Locally on Custom Dataset
มุมมอง 1.8K9 ชั่วโมงที่ผ่านมา
Fine-Tune LLM in VS Code AI Toolkit Locally on Custom Dataset
AI Toolkit for VScode - Install Locally - Run LLMs Locally in Windows
มุมมอง 2.9K9 ชั่วโมงที่ผ่านมา
AI Toolkit for VScode - Install Locally - Run LLMs Locally in Windows
What is Grokking and Over-Fitting of an LLM
มุมมอง 4029 ชั่วโมงที่ผ่านมา
What is Grokking and Over-Fitting of an LLM
I'm amazed at how you manage to consistently raise the bar with each video.
Can it be converted to srt?
would have to check when time permits
Thanks for sharing, it helps me a lot!
Glad it helped!
start with error nodes When loading the graph, the following node types were not found: ModelSamplingSD3 TripleCLIPLoader EmptySD3LatentImage Nodes that have failed to load will show as red on the graph.
Oh, I'm sorry I didn't update to the latest version.
cheers
How this localhost site can be accessed from another computer,how to publish pls guide
would need to check when time permits
you can use your wifi's public ip or use server like gcp or aws with public ip
This is a great video but I am having difficulties setting up my environment correctly. I keep getting a "Conda not detected" error in my WSL environment but I am able to make calls to conda in the command line. I updated the settings.json file in the ubuntu environment all sorts of things. It seems like an issue with the AI Toolkit not recognizing conda. Thoughts or advice?
would need to check when time permits
How can I download this ??
would need to check when time permits
🔥How to Install ComfyUI th-cam.com/video/BQmeLys7vZI/w-d-xo.html
Kindly also make tutorial how to create and use workflow
would need to check when time permits
You gotta use Silly Tavern if you're doing local RP!
sure
from llmware.configs import LLMWareConfig from llmware.retrieval import Query from llmware.library import Library LLMWareConfig().set_active_db("sqlite") LLMWareConfig().set_config("debug_mode", 2) library = Library().create_new_library('my_llmware_library') library.add_files('/content/llmware_data/sample_files/mydata') updated_library_card = library.get_library_card() doc_count = updated_library_card["documents"] block_count = updated_library_card["blocks"] query_results = Query(library).text_query('Percy Jackson', result_count=10) for query_result in query_results: text = query_result["text"] file_source = query_result["file_source"] page_number = query_result["page_num"] doc_id = query_result["doc_ID"] block_id = query_result["block_ID"] matches = query_result["matches"] print(text)
colab.research.google.com/drive/1_Y78pLx_wH4h1yyb_ovjCYGSVSHbICO_#scrollTo=UtaKHSONma2m
Can I use your discount code everytime or only once?
yes any time
is it possible to embed this transcription in TH-cam video?
would need to check when time permits
Now we know, Apple intelligence integrated with Mac OS either local or server, with optional Open GI chat….
sure
Still unsure what it is exactly
ok
Hello what are the minimal GPU VRAM recommended for running this model?
check the model card plz
It's giving me no cuda error
would need to check when time permits
@@fahdmirza solved it using control palette use the AI toolkit : validate , interpreter
Is it necessary openai api and gpu?
yes
getting error dbgpt_server.py': [Errno 2] No such file or directory
would need to check when time permits
Can't wait to add local models to it.
ok
can we do the same with llama2
would need to check when time permits
It’s not made by meta but by OpenAI 0:19
You are right, hard to edit now but hopefully your comment will help :)
Still i didn't get that setting an host part, How to setup that.....?
would need to check when time permits
@@fahdmirza i am really sorry sir i am an newbie I tried to Read documentation as well but still i didn't understand, so can u please explain me in detail
Hi!, i'm having this issue while follow your tutorial: "Your installed package `nvidia-ml-py` is corrupted. Skip patch functions `nvmlDeviceGet{Compute,Graphics,MPSCompute}RunningProcesses`. You may get incorrect or incomplete results. Please consider reinstall package `nvidia-ml-py` via `pip3 install --force-reinstall nvidia-ml-py nvitop`.", do you know how fix this?
would need to check when time permits
Very insightful!!!
Glad it was helpful!
npm i beffore npm run dev no? ;) thanks! i love whisper (pnpm i (better ;)) i hope this with option of whisperX for add timestamps to .srt :) and new version can translate automatic english to spanish :) not only spanish to english :(
Sure
Thank you Fahd !
You are welcome!
Is this available publicy for testing?
Not yet
sound is much better
It indeed is
Open source, but not for commercial use...
ok
Who cares
*Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. why ?????????????*
would need to check when time permits
Can it do live transcribing from an audio stream?
No, I dont think so
@@fahdmirza there is a github project collabora WhisperLive
Without running this method you can run llm 13b with vram 8 giga If that's not enough, you can run on it cpu and veam together
ok
Hardware's CPU supported instruction sets '' does not include CPU Manifest's instruction set 'AVX2'.. Wont open
would need to check when time permits
thanks, you can upload this code? i hope next videos with rag and other things :) for coding un vscode is better than codestral?
done
On Linux (Fedora 40 workstation) when i run the AI model codegemma:2b on Ollama it does not respond the way the other AI models do, instead it seems to be creating a .ipynb file. But i haven't been able to find it anywhere on my system. I've even done system-wide searches to no awail. Do you know where these files are saved by any chance?
would need to check when time permits
THANSK! good tool!!! :)
thanks
Is it a card rtx3050 It supports cODA 12, and can you make a video for run llm with cuda rtx3050
Sure , send me the RTX3050 and I will make it
How to use it in docker ? No video on internet showing it use in docker
would need to check when time permits
please tell me how to use a huggingface mode with an openai endpoint , anther question what is the best web agent to do web tasks
would need to check when time permits
great! how about Mac OS?
would need to check when time permits
Very useful. Thanks a lot
Glad it was helpful!
Hey Thanks for introducing this model to us. so this works on llm?? or some deep learning model ?? if it is llm then can you share how to deploy this on android device
would need to check when time permits
will phi or low resource model zip informations?
would need to check when time permits
Great! How does it compares to PrivateGPT and Anything LLM?
would need to check when time permits
This appears to be censored which is disporting.
Sure
Do you know how to train your own audio model? That would be dope
alerady did a video on it
has anyone tried it with ollama?
would need to check when time permits
how to convert these models to gguf format
would need to check when time permits