File size: 2,391 Bytes
01c904a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
class FastEsmConfig(PretrainedConfig):
model_type = "fast_esm"
def __init__(
self,
vocab_size=None,
mask_token_id=None,
pad_token_id=None,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=1026,
initializer_range=0.02,
layer_norm_eps=1e-12,
position_embedding_type="absolute",
emb_layer_norm_before=None,
**kwargs,
):
super().__init__(pad_token_id=pad_token_id, mask_token_id=mask_token_id, **kwargs)
self.vocab_size = vocab_size
self.hidden_size = hidden_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.intermediate_size = intermediate_size
self.hidden_dropout_prob = hidden_dropout_prob
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.max_position_embeddings = max_position_embeddings
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.position_embedding_type = position_embedding_type
self.emb_layer_norm_before = emb_layer_norm_before
def to_dict(self):
"""
Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
Returns:
`Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
"""
output = super().to_dict()
return output
def get_default_vocab_list():
return (
"<cls>",
"<pad>",
"<eos>",
"<unk>",
"L",
"A",
"G",
"V",
"S",
"E",
"R",
"T",
"I",
"D",
"P",
"K",
"Q",
"N",
"F",
"Y",
"M",
"H",
"W",
"C",
"X",
"B",
"U",
"Z",
"O",
".",
"-",
"<null_1>",
"<mask>",
)
|