|
from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
|
class FairseqT5Config(PretrainedConfig): |
|
model_type = "fairseq_t5" |
|
keys_to_ignore_at_inference = ["past_key_values"] |
|
attribute_map = {"hidden_size": "d_model", "num_attention_heads": "num_heads", "num_hidden_layers": "num_layers"} |
|
|
|
def __init__( |
|
self, |
|
vocab_size=64518, |
|
d_model=768, |
|
d_kv=64, |
|
d_ff=3072, |
|
num_layers=6, |
|
num_decoder_layers=None, |
|
num_heads=8, |
|
relative_attention_num_buckets=32, |
|
relative_attention_max_distance=128, |
|
max_positions=1024, |
|
dropout_rate=0.1, |
|
layer_norm_epsilon=1e-6, |
|
initializer_factor=1.0, |
|
feed_forward_proj="relu", |
|
is_encoder_decoder=True, |
|
use_cache=True, |
|
pad_token_id=1, |
|
eos_token_id=2, |
|
**kwargs |
|
): |
|
self.vocab_size = vocab_size |
|
self.d_model = d_model |
|
self.d_kv = d_kv |
|
self.d_ff = d_ff |
|
self.num_layers = num_layers |
|
self.num_decoder_layers = ( |
|
num_decoder_layers if num_decoder_layers is not None else self.num_layers |
|
) |
|
self.num_heads = num_heads |
|
self.relative_attention_num_buckets = relative_attention_num_buckets |
|
self.relative_attention_max_distance = relative_attention_max_distance |
|
self.max_positions = max_positions |
|
self.dropout_rate = dropout_rate |
|
self.layer_norm_epsilon = layer_norm_epsilon |
|
self.initializer_factor = initializer_factor |
|
self.feed_forward_proj = feed_forward_proj |
|
self.use_cache = use_cache |
|
super().__init__( |
|
pad_token_id=pad_token_id, |
|
eos_token_id=eos_token_id, |
|
is_encoder_decoder=is_encoder_decoder, |
|
**kwargs, |
|
) |
