File size: 10,324 Bytes
1ce5e18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
# coding=utf-8
# Copyright 2022 Salesforce authors, The EleutherAI, and HuggingFace Teams. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" CodeGen model configuration"""
from collections import OrderedDict
from typing import Any, List, Mapping, Optional

from ... import PreTrainedTokenizer, TensorType, is_torch_available
from ...configuration_utils import PretrainedConfig
from ...onnx import OnnxConfigWithPast, PatchingSpec
from ...utils import logging


logger = logging.get_logger(__name__)


CODEGEN_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "Salesforce/codegen-350M-nl": "https://huggingface.co/Salesforce/codegen-350M-nl/resolve/main/config.json",
    "Salesforce/codegen-350M-multi": "https://huggingface.co/Salesforce/codegen-350M-multi/resolve/main/config.json",
    "Salesforce/codegen-350M-mono": "https://huggingface.co/Salesforce/codegen-350M-mono/resolve/main/config.json",
    "Salesforce/codegen-2B-nl": "https://huggingface.co/Salesforce/codegen-2B-nl/resolve/main/config.json",
    "Salesforce/codegen-2B-multi": "https://huggingface.co/Salesforce/codegen-2B-multi/resolve/main/config.json",
    "Salesforce/codegen-2B-mono": "https://huggingface.co/Salesforce/codegen-2B-mono/resolve/main/config.json",
    "Salesforce/codegen-6B-nl": "https://huggingface.co/Salesforce/codegen-6B-nl/resolve/main/config.json",
    "Salesforce/codegen-6B-multi": "https://huggingface.co/Salesforce/codegen-6B-multi/resolve/main/config.json",
    "Salesforce/codegen-6B-mono": "https://huggingface.co/Salesforce/codegen-6B-mono/resolve/main/config.json",
    "Salesforce/codegen-16B-nl": "https://huggingface.co/Salesforce/codegen-16B-nl/resolve/main/config.json",
    "Salesforce/codegen-16B-multi": "https://huggingface.co/Salesforce/codegen-16B-multi/resolve/main/config.json",
    "Salesforce/codegen-16B-mono": "https://huggingface.co/Salesforce/codegen-16B-mono/resolve/main/config.json",
}


class CodeGenConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`CodeGenModel`]. It is used to instantiate a
    CodeGen 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 CodeGen
    [Salesforce/codegen-2B-mono](https://huggingface.co/Salesforce/codegen-2B-mono) architecture. Configuration objects
    inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from
    [`PretrainedConfig`] for more information.

    Args:
        vocab_size (`int`, *optional*, defaults to 50400):
            Vocabulary size of the CodeGen model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`CodeGenModel`].
        n_positions (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        n_embd (`int`, *optional*, defaults to 4096):
            Dimensionality of the embeddings and hidden states.
        n_layer (`int`, *optional*, defaults to 28):
            Number of hidden layers in the Transformer encoder.
        n_head (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        rotary_dim (`int`, *optional*, defaults to 64):
            Number of dimensions in the embedding that Rotary Position Embedding is applied to.
        n_inner (`int`, *optional*, defaults to None):
            Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
        activation_function (`str`, *optional*, defaults to `"gelu_new"`):
            Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`.
        resid_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        embd_pdrop (`int`, *optional*, defaults to 0.1):
            The dropout ratio for the embeddings.
        attn_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
            The epsilon to use in the layer normalization layers.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).

    Example:

    ```python
    >>> from transformers import CodeGenConfig, CodeGenModel

    >>> # Initializing a CodeGen 6B configuration
    >>> configuration = CodeGenConfig()

    >>> # Initializing a model (with random weights) from the configuration
    >>> model = CodeGenModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""
    model_type = "codegen"
    attribute_map = {
        "max_position_embeddings": "n_positions",
        "hidden_size": "n_embd",
        "num_attention_heads": "n_head",
        "num_hidden_layers": "n_layer",
    }

    def __init__(
        self,
        vocab_size=50400,
        n_positions=2048,
        n_ctx=2048,
        n_embd=4096,
        n_layer=28,
        n_head=16,
        rotary_dim=64,
        n_inner=None,
        activation_function="gelu_new",
        resid_pdrop=0.0,
        embd_pdrop=0.0,
        attn_pdrop=0.0,
        layer_norm_epsilon=1e-5,
        initializer_range=0.02,
        use_cache=True,
        bos_token_id=50256,
        eos_token_id=50256,
        tie_word_embeddings=False,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.n_ctx = n_ctx
        self.n_positions = n_positions
        self.n_embd = n_embd
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_inner = n_inner
        self.rotary_dim = rotary_dim
        self.activation_function = activation_function
        self.resid_pdrop = resid_pdrop
        self.embd_pdrop = embd_pdrop
        self.attn_pdrop = attn_pdrop
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.use_cache = use_cache

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id

        super().__init__(
            bos_token_id=bos_token_id, eos_token_id=eos_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs
        )


# Copied from transformers.models.gpt2.configuration_gpt2.GPT2OnnxConfig
class CodeGenOnnxConfig(OnnxConfigWithPast):
    def __init__(
        self,
        config: PretrainedConfig,
        task: str = "default",
        patching_specs: List[PatchingSpec] = None,
        use_past: bool = False,
    ):
        super().__init__(config, task=task, patching_specs=patching_specs, use_past=use_past)
        if not getattr(self._config, "pad_token_id", None):
            # TODO: how to do that better?
            self._config.pad_token_id = 0

    @property
    def inputs(self) -> Mapping[str, Mapping[int, str]]:
        common_inputs = OrderedDict({"input_ids": {0: "batch", 1: "sequence"}})
        if self.use_past:
            self.fill_with_past_key_values_(common_inputs, direction="inputs")
            common_inputs["attention_mask"] = {0: "batch", 1: "past_sequence + sequence"}
        else:
            common_inputs["attention_mask"] = {0: "batch", 1: "sequence"}

        return common_inputs

    @property
    def num_layers(self) -> int:
        return self._config.n_layer

    @property
    def num_attention_heads(self) -> int:
        return self._config.n_head

    def generate_dummy_inputs(
        self,
        tokenizer: PreTrainedTokenizer,
        batch_size: int = -1,
        seq_length: int = -1,
        is_pair: bool = False,
        framework: Optional[TensorType] = None,
    ) -> Mapping[str, Any]:
        common_inputs = super(OnnxConfigWithPast, self).generate_dummy_inputs(
            tokenizer, batch_size=batch_size, seq_length=seq_length, is_pair=is_pair, framework=framework
        )

        # We need to order the input in the way they appears in the forward()
        ordered_inputs = OrderedDict({"input_ids": common_inputs["input_ids"]})

        # Need to add the past_keys
        if self.use_past:
            if not is_torch_available():
                raise ValueError("Cannot generate dummy past_keys inputs without PyTorch installed.")
            else:
                import torch

                batch, seqlen = common_inputs["input_ids"].shape
                # Not using the same length for past_key_values
                past_key_values_length = seqlen + 2
                past_shape = (
                    batch,
                    self.num_attention_heads,
                    past_key_values_length,
                    self._config.hidden_size // self.num_attention_heads,
                )
                ordered_inputs["past_key_values"] = [
                    (torch.zeros(past_shape), torch.zeros(past_shape)) for _ in range(self.num_layers)
                ]

        ordered_inputs["attention_mask"] = common_inputs["attention_mask"]
        if self.use_past:
            mask_dtype = ordered_inputs["attention_mask"].dtype
            ordered_inputs["attention_mask"] = torch.cat(
                [ordered_inputs["attention_mask"], torch.ones(batch, past_key_values_length, dtype=mask_dtype)], dim=1
            )

        return ordered_inputs

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