#3-Deployment Of Huggingface OpenSource LLM Models In AWS Sagemakers With Endpoints

Рет қаралды 32,114

Krish Naik

Күн бұрын

Пікірлер

@krishnaik06 8 ай бұрын

Check out the complete p[laylist of GenAI on AWS Cloud Playlist: kzbin.info/www/bejne/aJ7EgZSHqtmWjdU

@__john663 8 ай бұрын

Hey krish bro, Is the groq completely free or there is any subscription or hidden charges?

@__john663 8 ай бұрын

Hi krish anna Can make a video using llama3 8b model with llama-index and chat engine because I need the ai is capable to document retrieval and general interactions. Is this capable to do

@KumR 7 ай бұрын

One request Krish. There is a separate playlist u added 3 months for bedrock. Could you merge those with this playlist too?

@intellectfactory 7 ай бұрын

IMPORTANT NOTE : When you create a Domain, user profile and launch any instance, make sure you turn off/pause the instance one you are done with your work. If you don't and just close the browser, the instance will still be running and you will be charged for it if it crosses the free tier limits. I did this mistake and got billed $52 and got to know about it only when I got the bill in my email. Make sure you check the Bills page regularly to see if you are being charged for any running instance.

@bornclasher1294 4 ай бұрын

Great information brother. Thank you soo much

@viswanathhemanth Ай бұрын

Yes. very important same thing happened to me as well

@oskee1334 9 күн бұрын

I did these two steps. Hopefully, that's all there is to it. 1. Stop the instance : SageMaker Studio -> Running Instances -> Stop instance (there is no delete button). 2. Delete the Endpoint : SageMaker Studio -> Inference Experience -> Endpoints

@classicemmaeasy2292 8 ай бұрын

Your consistency is contagious ❤💯

@THEINDIANSAVIOR 3 ай бұрын

It's been a great journey with your amazing lectures ❤❤. Th aka for the sincere work and helping . Sir one request Could you please create playlist for entire LLM. And Gen AI combined together So that we can easily come to know the continuity

@yogeshmagar452 8 ай бұрын

Krish Naik Respect Button❤

@AshishKumar-sj1ys 8 ай бұрын

Your tech news video was awsome. please make another ones on regular basics 🎉

@rsnoor 2 ай бұрын

Sir this is quiet useful and thanks for the step by step explanation. One kind request sir, i think you are shaking your legs continuously and that is shaking your video as well which is distracting, so please either your video even smaller if shaking legs is you mannerism sir.

@AnilKumar-im2ur 7 ай бұрын

Great work!, expecting your next video is to create one session to deploy LLM models using aws ec2 instance.

@rishitadavarthi4384 4 ай бұрын

@Raaj_ML 3 ай бұрын

Sorry Krish...Not sure why you were in a hurry towards the end in explaining that image_uri part...Not clear how is that different from the initial hub image deployment you were explaining..

@ne8123-g3x Ай бұрын

Hi, great work! Can you discuss how to add concurrency and scale it up? for example for deploying a embedding model to embed 100M vectors efficiently. Thanks

@austinduke8876 4 ай бұрын

Where does the model id come from? I looked for it on HuggingFace but I think I missed where that's listed for a given model

@torontoTamilan7 8 ай бұрын

Hi Sir , I'm mainly looking for your video on Gemma 7b fine-tuning in sagemaker and deploy as endpoint , it would be highly helpful if you can create a video for this . Step by step . Thanks a lot sir , I'm one of your huge fan . Great work.

@WanderingSatty 7 ай бұрын

Best moment 16:10 :)

@__john663 8 ай бұрын

Hey krish bro, Is the groq completely free or there is any subscription or hidden charges?

@__john663 8 ай бұрын

Hi krish anna Can make a video using llama3 8b model with llama-index and chat engine because I need the ai is capable to document retrieval and general interactions. Is this capable to do

@harshadapatke885 8 ай бұрын

Thanks for uploading it. One request to you- Can you please make videos on model quantization?

@SwethaSelvaraj-br6gi 8 ай бұрын

Can you make a video on serving LLM model BentoML

@jefinprince 8 ай бұрын

Can you make a video on creating a bedrock chatbot using langchain and streamlit with multiple knowledge bases and to select a particular knowledge base with a scroll down menu.