File size: 3,574 Bytes
f36c5fb 710d085 f36c5fb 9e92568 43f6405 f36c5fb 43f6405 f36c5fb a3e8ff1 3132114 a3e8ff1 8560bf5 f36c5fb 3f45a8d 2201866 264503f 2201866 264503f 05158d9 f36c5fb |
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 92 93 94 95 96 97 98 99 100 |
from transformers import PretrainedConfig
import torch
class ImpressoConfig(PretrainedConfig):
model_type = "stacked_bert"
def __init__(
self,
vocab_size=30522,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
intermediate_size=3072,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
type_vocab_size=2,
initializer_range=0.02,
layer_norm_eps=1e-12,
pad_token_id=0,
position_embedding_type="absolute",
use_cache=True,
classifier_dropout=None,
pretrained_config=None,
values_override=None,
label_map=None,
**kwargs,
):
super().__init__(pad_token_id=pad_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.hidden_act = hidden_act
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.type_vocab_size = type_vocab_size
self.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.position_embedding_type = position_embedding_type
self.use_cache = use_cache
self.classifier_dropout = classifier_dropout
self.pretrained_config = pretrained_config
self.label_map = label_map
self.values_override = values_override or {}
self.outputs = {
"logits": {"shape": [None, None, self.hidden_size], "dtype": "float32"}
}
@classmethod
def is_torch_support_available(cls):
"""
Indicate whether Torch support is available for this configuration.
Required for compatibility with certain parts of the Transformers library.
"""
return True
@classmethod
def patch_ops(self):
"""
A method required by some Hugging Face utilities to modify operator mappings.
Currently, it performs no operation and is included for compatibility.
Args:
ops: A dictionary of operations to potentially patch.
Returns:
The (unmodified) ops dictionary.
"""
return None
def generate_dummy_inputs(self, tokenizer, batch_size=1, seq_length=8, framework="pt"):
"""
Generate dummy inputs for testing or export.
Args:
tokenizer: The tokenizer used to tokenize inputs.
batch_size: Number of input samples in the batch.
seq_length: Length of each sequence.
framework: Framework ("pt" for PyTorch, "tf" for TensorFlow).
Returns:
Dummy inputs as a dictionary.
"""
if framework == "pt":
input_ids = torch.randint(
low=0,
high=self.vocab_size,
size=(batch_size, seq_length),
dtype=torch.long
)
attention_mask = torch.ones((batch_size, seq_length), dtype=torch.long)
return {"input_ids": input_ids, "attention_mask": attention_mask}
else:
raise ValueError("Framework '{}' not supported.".format(framework))
# Register the configuration with the transformers library
ImpressoConfig.register_for_auto_class()
|