Hacker News new | past | comments | ask | show | jobs | submit login

They probably shrunk the model from 175B to 17B. That's your 10:1 price reduction.



Wouldn't that almost certainly lead to measurable loss of capabilities?


If the model was quantized/distilled correctly, not for a large swath of use cases/problem domain. For anything where loss was not measured during distillation, very likely.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: