File size: 6,931 Bytes
cc9ca31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248a174
cc9ca31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248a174
cc9ca31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
from typing import Mapping
from transformers.configuration_utils import PretrainedConfig
from transformers.onnx import OnnxSeq2SeqConfigWithPast
from transformers.utils import logging


logger = logging.get_logger(__name__)


class T5MIMOConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`T5Model`] or a [`TFT5Model`]. It is used to
    instantiate a T5 model according to the specified arguments, defining the model architecture. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the T5
    [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Arguments:
        vocab_size (`int`, *optional*, defaults to 32128):
            Vocabulary size of the T5 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`T5Model`] or [`TFT5Model`].
        d_model (`int`, *optional*, defaults to 512):
            Size of the encoder layers and the pooler layer.
        d_kv (`int`, *optional*, defaults to 64):
            Size of the key, query, value projections per attention head. The `inner_dim` of the projection layer will
            be defined as `num_heads * d_kv`.
        d_ff (`int`, *optional*, defaults to 2048):
            Size of the intermediate feed forward layer in each `T5Block`.
        num_layers (`int`, *optional*, defaults to 6):
            Number of hidden layers in the Transformer encoder.
        num_decoder_layers (`int`, *optional*):
            Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set.
        num_heads (`int`, *optional*, defaults to 8):
            Number of attention heads for each attention layer in the Transformer encoder.
        relative_attention_num_buckets (`int`, *optional*, defaults to 32):
            The number of buckets to use for each attention layer.
        relative_attention_max_distance (`int`, *optional*, defaults to 128):
            The maximum distance of the longer sequences for the bucket separation.
        dropout_rate (`float`, *optional*, defaults to 0.1):
            The ratio for all dropout layers.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for classifier.
        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
            The epsilon used by the layer normalization layers.
        initializer_factor (`float`, *optional*, defaults to 1):
            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
            testing).
        feed_forward_proj (`string`, *optional*, defaults to `"relu"`):
            Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`. T5v1.1 uses the
            `"gated-gelu"` feed forward projection. Original T5 uses `"relu"`.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
    """

    model_type = "t5mimo"
    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=32128,
        d_model=512,
        d_kv=64,
        d_ff=2048,
        num_layers=6,
        num_decoder_layers=None,
        num_heads=8,
        relative_attention_num_buckets=32,
        relative_attention_max_distance=128,
        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=0,
        eos_token_id=1,
        decoder_start_token_id = 0,
        classifier_dropout=0.0,
        num_seqs=3,
        num_filters=64,
        is_mimo=True,
        **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
        )  # default = symmetry
        self.num_heads = num_heads
        self.relative_attention_num_buckets = relative_attention_num_buckets
        self.relative_attention_max_distance = relative_attention_max_distance
        self.dropout_rate = dropout_rate
        self.classifier_dropout = classifier_dropout
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_factor = initializer_factor
        self.feed_forward_proj = feed_forward_proj
        self.use_cache = use_cache
        self.num_seqs = num_seqs
        self.num_filters = num_filters
        self.is_mimo = is_mimo

        act_info = self.feed_forward_proj.split("-")
        self.dense_act_fn = act_info[-1]
        self.is_gated_act = act_info[0] == "gated"

        if len(act_info) > 1 and act_info[0] != "gated" or len(act_info) > 2:
            raise ValueError(
                f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer. "
                "Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. "
                "'gated-gelu' or 'relu'"
            )

        # for backwards compatibility
        if feed_forward_proj == "gated-gelu":
            self.dense_act_fn = "gelu_new"

        super().__init__(
            pad_token_id=pad_token_id,
            eos_token_id=eos_token_id,
            decoder_start_token_id=decoder_start_token_id,
            is_encoder_decoder=is_encoder_decoder,
            **kwargs,
        )


class T5MIMOOnnxConfig(OnnxSeq2SeqConfigWithPast):
    @property
    def inputs(self) -> Mapping[str, Mapping[int, str]]:
        common_inputs = {
            "input_ids": {0: "batch", 1: "encoder_sequence"},
            "attention_mask": {0: "batch", 1: "encoder_sequence"},
        }
        if self.use_past:
            common_inputs["attention_mask"][1] = "past_encoder_sequence + sequence"
            common_inputs["decoder_input_ids"] = {0: "batch"}
            common_inputs["decoder_attention_mask"] = {0: "batch", 1: "past_decoder_sequence + sequence"}
        else:
            common_inputs["decoder_input_ids"] = {0: "batch", 1: "decoder_sequence"}
            common_inputs["decoder_attention_mask"] = {0: "batch", 1: "decoder_sequence"}

        if self.use_past:
            self.fill_with_past_key_values_(common_inputs, direction="inputs")

        return common_inputs

    @property
    def default_onnx_opset(self) -> int:
        return 13