Recognai

/

zeroshot_selectra_small

like 5

Follow

recognai 4

Hi! I have a hobby project (https://cometocoruna.com) where I scrape a lot of events, and I need to clasify what type of events they are.

I find this model good enough for my purposes, but I have a problem:

1. I'm going lean as I currently have no job currently, so I don't want to spend money on running this.

2. My server is an atom CPU + 4 GB Ram and no AVX sitting in my bedroom.

3. I don't think I will be able to use the free-tier API as I will make lots of inferences.

Do you think such model is viable to run in my hardware? The compute time in HF is fast but they run it in Xeons.