Correct Samplers Order?

#64
by KeyboardMasher - opened

The Readme recommends:

  • temperature = 1.0
  • top_p = 0.95
  • top_k = 64

But HF Transformers applies them in different order:

  • temperature
  • top_k
  • top_p

Llama.cpp applies them in yet another different order unless --samplers argument is used (which no one does):

  • top_k
  • top_p
  • temperature

All that changes the model behavior.
Which order is correct?

Thanks.

Sign up or log in to comment