Thanks for this!!! However, this could have been even better if you gave an actual demo on a notebook of how you would approach and modify a dataset. Or creating a dataset with the Evol-Instruct technique or the orca's approach of creating a data set. Still great content though
4090 ti is straining under 4-bit quantized 30-b version. Reasonable token speed though . ROCm coming to 7900 XTX, a card that is practically 1/2 the price of the 4090 (essentially, you'll have free electricity consumption for quite some time when you plan in the price difference). Taken all together you'll have cca 600-700 Watt per hour power consumption when the model is running. All in all you'll have a great AI toy for under 3,000-3,500 US$ (Ryzen 9 16 core, 32 thread and all combined).
your channel is gold, but unfortunately there is no clear path to walk through the videos for a beginner who has no idea where to start and where to go after
Good remark. In the next days (maybe at the weekend) a new introduction video will be published, where I try to explain basic methods, techniques, software on how to start with generative AI systems like GPT-4. Thank you!
Thanks for this!!! However, this could have been even better if you gave an actual demo on a notebook of how you would approach and modify a dataset. Or creating a dataset with the Evol-Instruct technique or the orca's approach of creating a data set. Still great content though
Nice!
hey, have you done or recomend any video regarding the hw to run your onpremise llm? or cloud?
@09:05 is a thing of legend.
is there open source datasets for arabic language ?
🤩👍
Hi, I'm enjoying the videos, do you have a discord server or any way to get in cotact with you personally? Thank you!
How can i optimise data content with my personal data ?
I think the pricing is bit off, you can get A100 80GB for lot less than $5/h
Where can I get it for $5/h
@@adhingafredrick7600 Runpod has H100 for 4.29 and A100 for 1.84
4090 ti is straining under 4-bit quantized 30-b version. Reasonable token speed though . ROCm coming to 7900 XTX, a card that is practically 1/2 the price of the 4090 (essentially, you'll have free electricity consumption for quite some time when you plan in the price difference). Taken all together you'll have cca 600-700 Watt per hour power consumption when the model is running. All in all you'll have a great AI toy for under 3,000-3,500 US$ (Ryzen 9 16 core, 32 thread and all combined).
your channel is gold, but unfortunately there is no clear path to walk through the videos for a beginner who has no idea where to start and where to go after
Good remark. In the next days (maybe at the weekend) a new introduction video will be published, where I try to explain basic methods, techniques, software on how to start with generative AI systems like GPT-4. Thank you!
thanks, this is very usefull
Glad it was helpful!
6:25 that's not that expensive