Open Minami-su opened 1 month ago
https://mobiusml.github.io/hqq_blog/
HQQ is a fast and accurate model quantizer that skips the need for calibration data. It's super simple to implement (just a few lines of code for the optimizer). It can crunch through quantizing the Llama2-70B model in only 4 minutes! 🚀
No response
🚀 The feature, motivation and pitch
https://mobiusml.github.io/hqq_blog/
HQQ is a fast and accurate model quantizer that skips the need for calibration data. It's super simple to implement (just a few lines of code for the optimizer). It can crunch through quantizing the Llama2-70B model in only 4 minutes! 🚀
Alternatives
No response
Additional context
No response