learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-08-16 02:41:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

math comment fix

Browse Source
This commit is contained in:
Varuna Jayasiri
2021-10-21 13:37:13 +05:30
parent 14fb057045
commit d0c6b369fe
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
labml_nn/transformers/switch/experiment.py
View File

@ -114,7 +114,7 @@ class Configs(NLPAutoRegressionConfigs):
# Total number of tokens processed, $T$, in the current batch $\mathscr{B}$ # Total number of tokens processed, $T$, in the current batch $\mathscr{B}$
total = counts.sum(dim=-1, keepdims=True) total = counts.sum(dim=-1, keepdims=True)
# Fraction of tokens routed to each expert # Fraction of tokens routed to each expert
# $$f_i = \frac{1}{T} \sum_{x \in \mathscr{B}} \unicode{x1D7D9} \{ \mathop{argmax} p(x), i \}$$ # $$f_i = \frac{1}{T} \sum_{x \in \mathscr{B}} \mathbf{1} \{ \mathop{argmax} p(x), i \}$$
# $f_i$ is the count of tokens where the argmax of $p(x)$ is equal to $i$. # $f_i$ is the count of tokens where the argmax of $p(x)$ is equal to $i$.
route_frac = counts / total route_frac = counts / total
# Mean routing probability # Mean routing probability