juancopi81's picture
Add t5x and mt3 models
b100e1c
raw
history blame
371 Bytes
# T5.1.0 3B model.
include 't5x/examples/t5/t5_1_0/base.gin' # imports vocab, optimizer and model.
# ------------------- Network specification overrides --------------------------
network.Transformer.config = @network.T5Config()
network.T5Config:
emb_dim = 1024
num_heads = 32
num_encoder_layers = 24
num_decoder_layers = 24
head_dim = 128
mlp_dim = 16384