Software Engineering Courses (SECourses)•2y ago

Hey everyone! After doing a lot of work in the generative AI space I want to start investing in trai

Hey everyone! After doing a lot of work in the generative AI space I want to start investing in training an LLM to process input - like a chatbot as an example

EvanOP•2/2/24, 3:14 AM

Any good videos/articles on how to train my own?

EEvan Hey everyone! After doing a lot of work in the generative AI space I want to sta...

Furkan Gözükara SECourses•2/2/24, 9:13 AM

this is a good topic. sadly i couldnt find time yet

FFurkan Gözükara SECourses this is a good topic. sadly i couldnt find time yet

EvanOP•2/2/24, 9:18 PM

will report back, i did find this which claims to be the automatic 1111 UI for text models: https://github.com/oobabooga/text-generation-webui

GitHub

GitHub - oobabooga/text-generation-webui: A Gradio web UI for Large...

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models. - GitHub - oobabooga/text-generation-webui: A Gradio web UI for Large Language Mod...

KaanCan•2/4/24, 4:57 PM

Hello, I want to replace my AMD graphics card with an Nvidia graphics card for stable diffusion. I wanted to buy a 3080, but since my PSU is 600W, the healthiest and newest generation card I can go for is RTX 4060, but with 8GB VRAM, I'm not sure if it's sufficient for stable diffusion. Therefore, I'm torn between 3060 12GB and 4060 due to VRAM, as I don't have any other alternatives due to my PSU

KKaanCan Hello, I want to replace my AMD graphics card with an Nvidia graphics card for s...

Furkan Gözükara SECourses•2/4/24, 5:49 PM

try to go as much as possible VRAM

Furkan Gözükara SECourses•2/4/24, 5:49 PM

if your 600 watt is real

Furkan Gözükara SECourses•2/4/24, 5:49 PM

you can go with RTX 3090 too

Furkan Gözükara SECourses•2/4/24, 5:49 PM

at worst you can do some undervoltage

KaanCan•2/4/24, 6:01 PM

I consulted with my friend, and he also advised me to upgrade to a 3080 and change the PSU later, which didn't seem unreasonable. However, I'm concerned about the inadequacy of the PSU causing damage to other components in the system.

KKaanCan I consulted with my friend, and he also advised me to upgrade to a 3080 and chan...

Furkan Gözükara SECourses•2/4/24, 6:10 PM

i think it would just shut down pc

FFurkan Gözükara SECourses i think it would just shut down pc

KaanCan•2/4/24, 6:16 PM

Everyone I asked recommended getting the 3080, and if you also approve, then it would be best for me to go with the 3080

KKaanCan Everyone I asked recommended getting the 3080, and if you also approve, then it ...

Furkan Gözükara SECourses•2/4/24, 6:17 PM

how much vram it has?

FFurkan Gözükara SECourses how much vram it has?

KaanCan•2/4/24, 6:18 PM

10gb

KKaanCan 10gb

Furkan Gözükara SECourses•2/4/24, 6:18 PM

i would buy RTX 4060 - 16 GB

Furkan Gözükara SECourses•2/4/24, 6:18 PM

much better

Furkan Gözükara SECourses•2/4/24, 6:18 PM

look for it

FFurkan Gözükara SECourses i would buy RTX 4060 - 16 GB

KaanCan•2/4/24, 6:20 PM

I can't buy anything within my budget except 3080

KKaanCan I can't buy anything within my budget except 3080

Furkan Gözükara SECourses•2/4/24, 6:22 PM

i see

Furkan Gözükara SECourses•2/4/24, 6:22 PM

maybe used card?

KKaanCan Hello, I want to replace my AMD graphics card with an Nvidia graphics card for s...

ShaDeRzz•2/4/24, 11:46 PM

What video card do you have now? I have AMD RX 6800XT 16gb and it handles Lora's training and stable diffusion quite well. The only inconvenience is that I had to install Ubuntu 20.04 on a second disk in order to have hardware acceleration

SShaDeRzz What video card do you have now? I have AMD RX 6800XT 16gb and it handles Lora's...

Furkan Gözükara SECourses•2/5/24, 12:15 AM

what are your second / it speed per iteration speed

Jillani SoftTech•2/5/24, 5:13 AM

Hey Everyone today I am recently sharing my new updated blog post please check and share your feedback.

https://jillanisofttech.medium.com/revolutionizing-llms-with-rag-navigating-the-new-frontier-in-ai-knowledge-and-trust-1b68fc3b53ec
ai

Medium

Revolutionizing LLMs with RAG: Navigating the New Frontier in AI Kn...

Muhammad Ghulam Jillani(Jillani SoftTech), Senior Data Scientist and Machine Learning Engineer

SShaDeRzz What video card do you have now? I have AMD RX 6800XT 16gb and it handles Lora's...

KaanCan•2/5/24, 9:52 AM

I use rx6600 and my operating system is Linux but I had to use it with docker because it was arch linux. When I installed stable diffusion directly to the system, it did not recognise the video card and worked with the processor. Somehow I managed to run stable diffusion with the video card using docker, but this time 512x512 20 step outputs took 60-90 seconds and after 4-5 outputs, the photos were distorted. Even when I tried with a proper seed and prompt, I kept getting corrupted outputs, and I was getting a 'cuda out of memory' error at the slightest setting change. I thought these speeds were normal, until I talked to someone using stable diffusion with a 3050 mobile graphics card who mentioned that he was getting outputs between 2-5 seconds. That's when I decided that I should definitely switch to NVIDIA.

JJillani SoftTech Hey Everyone today I am recently sharing my new updated blog post please check a...

Furkan Gözükara SECourses•2/5/24, 10:54 AM

nice thanks

KKaanCan I use rx6600 and my operating system is Linux but I had to use it with docker be...

Furkan Gözükara SECourses•2/5/24, 10:54 AM

true don't waste time with AMD if you are into AI

Dazzastrous [4090]•2/6/24, 10:49 PM

https://anythinginanyscene.github.io/?ref=aiartweekly#paper-outdoor-results

Anything in Any Scene

Photorealistic Video Object Insertion

mikemenders•2/7/24, 2:39 PM

Isn't there a decent, AI, melody generator that can be used offline and the music will have a beginning and an end? Online services have a bunch, and Wondershare already gives you one for Filmora, but no such thing for offline use? The Audiocraft/MusicGen/Magnet line is forgettable, a disaster what it generates.

Mmikemenders Isn't there a decent, AI, melody generator that can be used offline and the musi...

Furkan Gözükara SECourses•2/7/24, 10:53 PM

we have auto installers for audiocraft plus

Furkan Gözükara SECourses•2/7/24, 10:53 PM

you tried it?

Furkan Gözükara SECourses•2/7/24, 10:54 PM

https://www.patreon.com/posts/ai-music-auto-84334460

Patreon

Auto Installer For AudioCraft Plus - MusicGen - AudioGen - An All-i...

Patreon is empowering a new generation of creators.
Support and engage with artists and creators as they live out their passions!

bobylasticot•2/8/24, 1:51 AM

Hello @Furkan Gözükara SECourses do you have notebook for deepfake on your patreon? Interested to suscribe if yes

Bbobylasticot Hello <@205854764540362752> do you have notebook for deepfake on your patreon? I...

Furkan Gözükara SECourses•2/8/24, 10:59 AM

we have notebook for google colab. and i have auto installer for runpod

Furkan Gözükara SECourses•2/8/24, 10:59 AM

what else you need?

FFurkan Gözükara SECourses we have notebook for google colab. and i have auto installer for runpod

bobylasticot•2/9/24, 6:21 AM

Sorry I am still beginer , for what usage google colab

bobylasticot•2/9/24, 6:21 AM

BTW your vidéo are so Nice I will still sub to patron on the weekend to support ur good work

Bbobylasticot BTW your vidéo are so Nice I will still sub to patron on the weekend to support ...

Furkan Gözükara SECourses•2/9/24, 2:06 PM

awesome ty so much

Bbobylasticot Sorry I am still beginer , for what usage google colab

Furkan Gözükara SECourses•2/9/24, 2:06 PM

to deep fake . actually what we are doing is face transfer

Dazzastrous [4090]•2/13/24, 12:01 AM

revisiting pixart, impressive detail

DDazzastrous [4090]revisiting pixart, impressive detail

Furkan Gözükara SECourses•2/13/24, 12:08 AM

yep it is great model

Furkan Gözükara SECourses•2/13/24, 12:08 AM

just needed to trained with more images

Jillani SoftTech•2/13/24, 4:16 AM

Hey Everyone today I am recently sharing my new updated blog post please check and share your feedback.

https://jillanisofttech.medium.com/in-depth-data-pipeline-overview-1e8a8dece9ee
ai

Medium

In-Depth Data Pipeline Overview

Muhammad Ghulam Jillani(Jillani SoftTech), Senior Data Scientist and Machine Learning Engineer

Tacite•2/14/24, 9:19 AM

Hey @Furkan Gözükara SECourses, I see you’re knowledgeable about LLM and image or video AI, never tried voice AI ?

TTacite Hey <@205854764540362752>, I see you’re knowledgeable about LLM and image or vid...

Furkan Gözükara SECourses•2/14/24, 6:54 PM

i got experience with ai voice

Furkan Gözükara SECourses•2/14/24, 6:54 PM

for llm some degree

Dradik•2/16/24, 3:50 AM

https://openai.com/sora this is insane..

Sora: Creating video from text

RETRO•2/18/24, 12:18 AM

GUYS! i need your help! does anyone know of a good site/tool/workflow that i can use to bring more detail and restore an old scanned photo?

I have my moms birthday tomorrow and this would mean the absolute world to me if someone can help me figure out a way to restore these old images to present her with for her birthday

@Furkan Gözükara SECourses (sorry for ping)

RRETRO GUYS! i need your help! does anyone know of a good site/tool/workflow that i can...

Furkan Gözükara SECourses•2/18/24, 12:23 AM

this is also in my interest

Furkan Gözükara SECourses•2/18/24, 12:23 AM

but i dont know yet

zaubermax•2/18/24, 8:08 AM

Hello there.

I wanted to try the Ozen Toolkit: https://github.com/FurkanGozukara/ozen-toolkit.

I encountered the error below:
"Downgrade the protobuf package to 3.20.x or lower."
"Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower)."

I deleted the Conda environment and added "protobuf <= 3.20.3" to the requirements.txt. After setting it up again, it works with this change.

However, I am not sure if this is the appropriate fix as I am not a programmer. Perhaps someone more versed in Python can make a pull request with the correct fix.

zaubermax•2/18/24, 8:11 AM

Furthermore the whisper-large-v2 is set as default. This model could be changed to whisper-large-v3 which is the newer version

Hey everyone! After doing a lot of work in the generative AI space I want to start investing in trai

Similar Threads