SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

docs: fix minor typo (#13289)

Browse Source 
`at` should be `a1`
This commit is contained in:
Jake Tae
2021-08-31 06:49:05 -04:00
committed by GitHub
parent 066fd047cc
commit 180c6de6a6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/parallelism.md
View File

@@ -58,7 +58,7 @@ a0 | b0 | c0
a1 | b1 | c1 a1 | b1 | c1
a2 | b2 | c2 a2 | b2 | c2
``` ```
Layer La has weights a0, at and a2. Layer La has weights a0, a1 and a2.
If we have 3 GPUs, the Sharded DDP (= Zero-DP) splits the model onto 3 GPUs like so: If we have 3 GPUs, the Sharded DDP (= Zero-DP) splits the model onto 3 GPUs like so: