You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
After quantization of LLaMA2-7b, I notice that total parameters of the quantized model is around 1.1B while the original dense model has around 6.7B parameters. It seems that the code also prunes LLM weights. Any idea why weights are additionally removed?
Thanks a lot!
The text was updated successfully, but these errors were encountered:
After quantization of LLaMA2-7b, I notice that total parameters of the quantized model is around 1.1B while the original dense model has around 6.7B parameters. It seems that the code also prunes LLM weights. Any idea why weights are additionally removed?
Thanks a lot!
The text was updated successfully, but these errors were encountered: