"...text-generation-inference.git" did not exist on "647ae7a7d32ae64e6b64956d83e7c5a96e854283"
Commit 58e2c449 authored by alexeib's avatar alexeib Committed by Myle Ott
Browse files

default dropout to correct value for big transformer

parent bf47b956
......@@ -435,6 +435,7 @@ def transformer_vaswani_wmt_en_de_big(args):
args.decoder_ffn_embed_dim = 4096
args.decoder_layers = 6
args.decoder_attention_heads = 16
args.dropout = 0.3
@register_model_architecture('transformer', 'transformer_wmt_en_de_big')
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment