quantize_stats: print rmse and max error as fraction of <x>

ikawrakow / ik_llama.cpp

llama.cpp clone with additional SOTA quants and improved CPU performance

MIT License

57 stars 4 forks source link

quantize_stats: print rmse and max error as fraction of <x> #21

Closed ikawrakow closed 1 month ago

ikawrakow commented 1 month ago

This allows for a better comparison between different models or different tensors of the same model where the magnitude of the model weights may differ.