The quantization will greatly reduce multilingual capabilities
Ion_GPT
joined 11 months ago
I got the idea, but I think your example is bad. History is something that is changing really slow and is not even changing, it just increases.
No. V100 is not ampere architecture and for that price is simply not worth. 3090 is cheaper and has 24 gb
Depending on the task. For anything related to multilingual, like translating, the quant will destroy the model. I suspect that this is because the sampling data used during the process is all English.
I plan to invest $50000 over the next 6 months to upgrade my home lab to be able to run better models but mostly to be able to store models. I also plan to create a torrent service fully dedicated to share models.
I hope that I will never need all this, but there is no way that I am going to drop everything due to some stupid legislation
If the account has 100k bots following it and the bots will keep liking all the posts, the value is above 100$.
However, most probably it is a scam and either the stats are faked, either you will not receive the account, either it will be reported as hacked, whatever other scam you might think of.
Best case scenario, the bot network is real and the account really got those likes and followers and after you buy it the bot network is moving on to the next account and you are left with an account with 10 followers.
Do you have a prompt for translating?