From 96f060572eb48251d13691716dc1c74aaaa8472c Mon Sep 17 00:00:00 2001 From: Stanislaw Dunin-Horkawicz Date: Fri, 13 Sep 2024 16:24:11 +0200 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 19fda7a..e3e1d2e 100644 --- a/README.md +++ b/README.md @@ -64,7 +64,7 @@ In the examples above, `database` defines a directory where sequence embeddings The batch size (number of sequences per batch) is set with the `-bs` option. Setting `-bs` to `0` activates the adaptive mode, in which the batch size is set so that all included sequences have no more than 3000 residues (this value can be changed with `--res_per_batch`). -The use of `--gpu` is highly recommended for large datasets. To run `embeddings.py` on multiple GPUs, specify `-proc X` where `X` is the number of GPU devices you want to use. +The use of `--gpu` is highly recommended for large datasets. To run `embeddings.py` on multiple GPUs, specify `-nproc X` where `X` is the number of GPU devices you want to use. ### Checkpointing feature