Viewing profile — zshn25

[dead]

[dead]

It would be interesting to benchmark a short training / inference run on the latest of TPU vs. NVIDIA GPU per cost basis

Splitting TPUs into dedicated training vs inference chips feels like an admission that the bottleneck has shifted from FLOPs to memory bandwidth + latency. Are future gains to come…

Thank you for your kind words. Great catalog. I found WordFor already.

Open-source, free version of this is Stirling PDF https://github.com/Stirling-Tools/Stirling-PDF where you can do very accurate OCR while keep the formatting.

Stirling PDF https://github.com/Stirling-Tools/Stirling-PDF is a free self-hosted PDF tool that can do very accurate OCR while keeping the formatting.

I first compute the embeddings to the dictionaries and store these. At query-time, when the user inputs the description, its embeddings are again computed by a lighter model. Then …

[dead]

We all know the feeling: can’t remember the word but we know what it means. That’s why I built: WordFor - a reverse dictionary where you describe a concept and it suggests the word…

The comparison to automobiles changing streets is thrown around a lot. But I feel AI is fundamentally different. It is not a technological change like the internet which brought us…

Sorry, how did you calculate the 10.25B?

Got it. Thanks

~I see. What’s the 6?~ Nevermind, the other reply clears it

What do all the numbers 6-35B-A3B mean?