hi @krishnaik sir, this is a personal feedback .Have been following your videos and your amazing way of explaining things. Based on the same enrolled in one of the courses(generative AI) in ineuron.Though the topics covered are great, you definitely need to have a look at the articulation skills of the instructor.The quality is shockingly low and same is visible in the freecodecamp video as well.They are just throwing around some words while explaining key concepts and that too not very clearly. You are such a great teacher with extraordinary knowledge and we all believe in your brand but you should look into this as this was not a great experience.
Amazing Krish. Thankyou for sharing about GROQ. Came to know the importance of inferencing. Hope you will be uploading projects using GROQ inference engine soon 😊.
Sir, I feel olama was trying to achieve the same thing in terms of Inferencing time. It would be amazing to watch the real time Inferencing comparison b/w olama and Groq-LPU on top a open LLM model(s)
Many companies prefer not to utilize third-party APIs due to concerns about potential data leakage. I tried using Replicate API to use Llama2, but they rejected the proposal for this reason.
hello sir I am SAMBA MURTHY a MECHANICAL ENGINEER GRADUATE in passed out in 2019 have nearly 5 years of career gap (prepared for gate and some family health issues) and my job in past is not at all related to DATA SCIENCE. Now I have completed GOOGLE DATA ANALYTICS PROFESSIONAL CERTIFICATE PROGRAM in coursera. and also I have completed your recently upload ROAD MAP TO BECOME A DATA ANALYST IN 2024. SO Please Help me how to build the RESUME WITH RESPECT TO THE CAREER GAP OF 5 YEARS and HOW TO TO CRACK THE INTERVIEW WITH 5 YEARS CAREER GAP please PLEASE 🙏🏻🙏🏻🙏🏻🙏🏻🙏🏻🙏🏻
Krish - I like the video and agree with you however my point is that larger Language model like GPT4 will have slower inference time than a model like Gamma-7B. The actual comparison would be to host Gamma-7B on some other platform and compare time with Groq.
Parameter size doesn't just affect the "quality" of the model but also the inference time for output tokens. This is not an apples to apples comparison and it is weird to see a teacher make such statements with confidence.
![[Gegagedigedagedago] NEW Help Gegagedigedagedago Nugget escape from Nikocado Avocado Challenge](http://i.ytimg.com/vi/hJWnwRC2Fz8/mqdefault.jpg)
Probably the most important video for anyone who are preparing for Genertaive AI :)
Thank you Krish sir ! Your videos are amazing ...
hi @krishnaik sir, this is a personal feedback .Have been following your videos and your amazing way of explaining things.
Based on the same enrolled in one of the courses(generative AI) in ineuron.Though the topics covered are great, you definitely need to have a look at the articulation skills of the instructor.The quality is shockingly low and same is visible in the freecodecamp video as well.They are just throwing around some words while explaining key concepts and that too not very clearly.
You are such a great teacher with extraordinary knowledge and we all believe in your brand but you should look into this as this was not a great experience.
Always no words to explain your content ✨️ 😌 it's amazing
I wish I could give you a 1000 likes.
Thanks for making these videos!
Krish ! Your videos are amazing and I learned a lot about Langchain the most from your videos. Thank you!
Amazing video thanks Krish Sir
We are waiting for that video.. as a beginner we need that video a lot..
NSA is already ahead of the race. They are invisible and invincible. 😊
"Sentient World Simulation and NSA Surveillance - Exploiting Privacy to Predict the Future?" Google this and please read this article. 🤯
What does NSA means here ? Can you give the full form of it
@@Thinesh_Kumar I guess he’s talking about the National Security Agency? An intelligence arm of the US government
@@CyberEnigma yep, I too tried to checking through internet and chatbots. No relatable answers to that.
@thineshkumar5068 @CyberEnigma Google this "Sentient World Simulation and NSA Surveillance - Exploiting Privacy to Predict the Future?"
Amazing Krish. Thankyou for sharing about GROQ. Came to know the importance of inferencing. Hope you will be uploading projects using GROQ inference engine soon 😊.
one like from me for choosing such amazing topics.. waiting eagerly for ur next video on this with code for me to try on👍
Keep it up sir
really amazing thanks for sharing 😇😇
Sir, I feel olama was trying to achieve the same thing in terms of Inferencing time. It would be amazing to watch the real time Inferencing comparison b/w olama and Groq-LPU on top a open LLM model(s)
Hi Krish, thank you for your work. Could you make a video for fine tuning of a multimodal model for example for medical?
Thank you sir for sharing this video ❤❤
Thanks for sharing 😊😊
Need end to end project sir❤
Many companies prefer not to utilize third-party APIs due to concerns about potential data leakage. I tried using Replicate API to use Llama2, but they rejected the proposal for this reason.
amazing !! eagerly waiting for the project
Welcome
Amazing explanation Sir!!
🔥
Hello Sir , thanks for this video ❤❤
Kindly also teach us on llamaparse, qdrant, nomic embeddings etc for RAG system
Sir you said that next video will be AI engineer roadmap and with resources...
coming soon :)
Excellent video, Krish, I'd love to have access to the project that you mentioned. Please let me know if it's already available somewhere.
You are 🔥
Amazing work !!!
i give you 1000000 likes sir, Thank you so much for such a amazing videos.
how high school students can land internship or job in generative ai or ai in whole
Superb
please upload end to end project of this topic sir
Which gonna make fast in these too
1. ERA 1BIT
2.Or this grow
Really helpful video. Would love to see the code.
bro what about grok model in the race of llm
Ai vs ml vs Ds vs dl kiya select Karo sir. Samj nahi aa raha math bhi nahi ata. Pls reply 😭😭😭🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏
Gamechanger in the realm of GenAI
But, is it P NP problem? Because the time complexity?
hello sir I am SAMBA MURTHY a MECHANICAL ENGINEER GRADUATE in passed out in 2019 have nearly 5 years of career gap (prepared for gate and some family health issues) and my job in past is not at all related to DATA SCIENCE. Now I have completed GOOGLE DATA ANALYTICS PROFESSIONAL CERTIFICATE PROGRAM in coursera. and also I have completed your recently upload ROAD MAP TO BECOME A DATA ANALYST IN 2024. SO Please Help me how to build the RESUME WITH RESPECT TO THE CAREER GAP OF 5 YEARS and HOW TO TO CRACK THE INTERVIEW WITH 5 YEARS CAREER GAP please PLEASE 🙏🏻🙏🏻🙏🏻🙏🏻🙏🏻🙏🏻
Why aren't you trying Mistral?
Hi Krish, can we use this technology to train the llm also?
yes may be
The comparision is not fair vs GPT3.5/4
Gamma7B has 7 Billion parameters.
GPT3.5/4 has more than 1 trillion parameters.
Here the comparison is for inference not best llm
Krish - I like the video and agree with you however my point is that larger Language model like GPT4 will have slower inference time than a model like Gamma-7B.
The actual comparison would be to host Gamma-7B on some other platform and compare time with Groq.
Parameter size doesn't just affect the "quality" of the model but also the inference time for output tokens. This is not an apples to apples comparison and it is weird to see a teacher make such statements with confidence.
Groq is fast
if you know they used 700 chip to demo this what would you think? show a 1 chip by chip comparison okay?
groq has 64Mm of memoery per chip. does that surpise you?
People who disliked are those who bought shares in nvidia 😂😂
I am sure 64 mb of memory make it great