Adding all project files

venv/Lib/site-packages/transformers/models/deprecated/xlm_prophetnet/__init__.py

@@ -0,0 +1,28 @@
+# Copyright 2020 The HuggingFace Team. 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.
+from typing import TYPE_CHECKING
+
+from ....utils import _LazyModule
+from ....utils.import_utils import define_import_structure
+
+
+if TYPE_CHECKING:
+    from .configuration_xlm_prophetnet import *
+    from .modeling_xlm_prophetnet import *
+    from .tokenization_xlm_prophetnet import *
+else:
+    import sys
+
+    _file = globals()["__file__"]
+    sys.modules[__name__] = _LazyModule(__name__, _file, define_import_structure(_file), module_spec=__spec__)

venv/Lib/site-packages/transformers/models/deprecated/xlm_prophetnet/configuration_xlm_prophetnet.py

@@ -0,0 +1,181 @@
+# coding=utf-8
+# Copyright 2020 The Microsoft Authors and The HuggingFace Inc. team.
+#
+# 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.
+"""XLM-ProphetNet model configuration"""
+
+from typing import Callable, Optional, Union
+
+from ....configuration_utils import PretrainedConfig
+from ....utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class XLMProphetNetConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`XLMProphetNetModel`]. It is used to instantiate a
+    XLMProphetNet 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 XLMProphetNet
+    [microsoft/xprophetnet-large-wiki100-cased](https://huggingface.co/microsoft/xprophetnet-large-wiki100-cased)
+    architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        activation_dropout (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for activations inside the fully connected layer.
+        activation_function (`str` or `function`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"silu"` and `"gelu_new"` are supported.
+        vocab_size (`int`, *optional*, defaults to 30522):
+            Vocabulary size of the ProphetNET model. Defines the number of different tokens that can be represented by
+            the `inputs_ids` passed when calling [`XLMProphetNetModel`].
+        hidden_size (`int`, *optional*, defaults to 1024):
+            Dimensionality of the layers and the pooler layer.
+        encoder_ffn_dim (`int`, *optional*, defaults to 4096):
+            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
+        num_encoder_layers (`int`, *optional*, defaults to 12):
+            Number of encoder layers.
+        num_encoder_attention_heads (`int`, *optional*, defaults to 16):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        decoder_ffn_dim (`int`, *optional*, defaults to 4096):
+            Dimensionality of the `intermediate` (often named feed-forward) layer in decoder.
+        num_decoder_layers (`int`, *optional*, defaults to 12):
+            Number of decoder layers.
+        num_decoder_attention_heads (`int`, *optional*, defaults to 16):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        attention_dropout (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for the attention probabilities.
+        dropout (`float`, *optional*, defaults to 0.1):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        max_position_embeddings (`int`, *optional*, defaults to 512):
+            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).
+        init_std (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        add_cross_attention (`bool`, *optional*, defaults to `True`):
+            Whether cross-attention layers should be added to the model.
+        is_encoder_decoder (`bool`, *optional*, defaults to `True`):
+            Whether this is an encoder/decoder model.
+        pad_token_id (`int`, *optional*, defaults to 1)
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 0)
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2)
+            End of stream token id.
+        ngram (`int`, *optional*, defaults to 2)
+            Number of future tokens to predict. Set to 1 to be same as traditional Language model to predict next first
+            token.
+        num_buckets (`int`, *optional*, defaults to 32)
+            The number of buckets to use for each attention layer. This is for relative position calculation. See the
+            [T5 paper](see https://huggingface.co/papers/1910.10683) for more details.
+        relative_max_distance (`int`, *optional*, defaults to 128)
+            Relative distances greater than this number will be put into the last same bucket. This is for relative
+            position calculation. See the [T5 paper](see https://huggingface.co/papers/1910.10683) for more details.
+        disable_ngram_loss (`bool`, *optional*, defaults to `False`):
+            Whether be trained predicting only the next first token.
+        eps (`float`, *optional*, defaults to 0.0):
+            Controls the `epsilon` parameter value for label smoothing in the loss calculation. If set to 0, no label
+            smoothing is performed.
+        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 = "xlm-prophetnet"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    attribute_map = {
+        "num_attention_heads": "num_encoder_attention_heads",
+    }
+
+    def __init__(
+        self,
+        activation_dropout: Optional[float] = 0.1,
+        activation_function: Optional[Union[str, Callable]] = "gelu",
+        vocab_size: Optional[int] = 30522,
+        hidden_size: Optional[int] = 1024,
+        encoder_ffn_dim: Optional[int] = 4096,
+        num_encoder_layers: Optional[int] = 12,
+        num_encoder_attention_heads: Optional[int] = 16,
+        decoder_ffn_dim: Optional[int] = 4096,
+        num_decoder_layers: Optional[int] = 12,
+        num_decoder_attention_heads: Optional[int] = 16,
+        attention_dropout: Optional[float] = 0.1,
+        dropout: Optional[float] = 0.1,
+        max_position_embeddings: Optional[int] = 512,
+        init_std: Optional[float] = 0.02,
+        is_encoder_decoder: Optional[bool] = True,
+        add_cross_attention: Optional[bool] = True,
+        decoder_start_token_id: Optional[int] = 0,
+        ngram: Optional[int] = 2,
+        num_buckets: Optional[int] = 32,
+        relative_max_distance: Optional[int] = 128,
+        disable_ngram_loss: Optional[bool] = False,
+        eps: Optional[float] = 0.0,
+        use_cache: Optional[bool] = True,
+        pad_token_id: Optional[int] = 0,
+        bos_token_id: Optional[int] = 1,
+        eos_token_id: Optional[int] = 2,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.encoder_ffn_dim = encoder_ffn_dim
+        self.num_encoder_layers = num_encoder_layers
+        self.num_encoder_attention_heads = num_encoder_attention_heads
+        self.decoder_ffn_dim = decoder_ffn_dim
+        self.num_decoder_layers = num_decoder_layers
+        self.num_decoder_attention_heads = num_decoder_attention_heads
+        self.max_position_embeddings = max_position_embeddings
+        self.init_std = init_std  # Normal(0, this parameter)
+        self.activation_function = activation_function
+
+        # parameters for xlmprophetnet
+        self.ngram = ngram
+        self.num_buckets = num_buckets
+        self.relative_max_distance = relative_max_distance
+        self.disable_ngram_loss = disable_ngram_loss
+        self.eps = eps
+
+        # 3 Types of Dropout
+        self.attention_dropout = attention_dropout
+        self.activation_dropout = activation_dropout
+        self.dropout = dropout
+
+        self.use_cache = use_cache
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            is_encoder_decoder=is_encoder_decoder,
+            add_cross_attention=add_cross_attention,
+            decoder_start_token_id=decoder_start_token_id,
+            **kwargs,
+        )
+
+    @property
+    def num_hidden_layers(self) -> int:
+        return self.num_encoder_layers + self.num_decoder_layers
+
+    @num_hidden_layers.setter
+    def num_hidden_layers(self, value):
+        raise NotImplementedError(
+            "This model does not support the setting of `num_hidden_layers`. Please set `num_encoder_layers` and"
+            " `num_decoder_layers`."
+        )
+
+
+__all__ = ["XLMProphetNetConfig"]

venv/Lib/site-packages/transformers/models/deprecated/xlm_prophetnet/tokenization_xlm_prophetnet.py

@@ -0,0 +1,322 @@
+# coding=utf-8
+# Copyright 2020 The Microsoft Authors and The HuggingFace Inc. team.
+#
+# 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.
+
+import collections
+import os
+from shutil import copyfile
+from typing import Any, Optional
+
+from ....tokenization_utils import PreTrainedTokenizer
+from ....utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+SPIECE_UNDERLINE = "▁"
+
+VOCAB_FILES_NAMES = {"vocab_file": "prophetnet.tokenizer"}
+
+
+def load_vocab(vocab_file):
+    """Loads a vocabulary file into a dictionary."""
+    vocab = collections.OrderedDict()
+    with open(vocab_file, "r", encoding="utf-8") as reader:
+        tokens = reader.readlines()
+    for index, token in enumerate(tokens):
+        token = token.rstrip("\n")
+        vocab[token] = index
+    return vocab
+
+
+class XLMProphetNetTokenizer(PreTrainedTokenizer):
+    """
+    Adapted from [`RobertaTokenizer`] and [`XLNetTokenizer`]. Based on
+    [SentencePiece](https://github.com/google/sentencepiece).
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+        bos_token (`str`, *optional*, defaults to `"[SEP]"`):
+            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
+
+            <Tip>
+
+            When building a sequence using special tokens, this is not the token that is used for the beginning of
+            sequence. The token used is the `cls_token`.
+
+            </Tip>
+
+        eos_token (`str`, *optional*, defaults to `"[SEP]"`):
+            The end of sequence token.
+
+            <Tip>
+
+            When building a sequence using special tokens, this is not the token that is used for the end of sequence.
+            The token used is the `sep_token`.
+
+            </Tip>
+
+        sep_token (`str`, *optional*, defaults to `"[SEP]"`):
+            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
+            sequence classification or for a text and a question for question answering. It is also used as the last
+            token of a sequence built with special tokens.
+        unk_token (`str`, *optional*, defaults to `"[UNK]"`):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead.
+        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
+            The token used for padding, for example when batching sequences of different lengths.
+        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
+            The classifier token which is used when doing sequence classification (classification of the whole sequence
+            instead of per-token classification). It is the first token of the sequence when built with special tokens.
+        mask_token (`str`, *optional*, defaults to `"[MASK]"`):
+            The token used for masking values. This is the token used when training this model with masked language
+            modeling. This is the token which the model will try to predict.
+        sp_model_kwargs (`dict`, *optional*):
+            Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
+            SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
+            to set:
+
+            - `enable_sampling`: Enable subword regularization.
+            - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.
+
+              - `nbest_size = {0,1}`: No sampling is performed.
+              - `nbest_size > 1`: samples from the nbest_size results.
+              - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
+                using forward-filtering-and-backward-sampling algorithm.
+
+            - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
+              BPE-dropout.
+
+    Attributes:
+        sp_model (`SentencePieceProcessor`):
+            The *SentencePiece* processor that is used for every conversion (string, tokens and IDs).
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file,
+        bos_token="[SEP]",
+        eos_token="[SEP]",
+        sep_token="[SEP]",
+        unk_token="[UNK]",
+        pad_token="[PAD]",
+        cls_token="[CLS]",
+        mask_token="[MASK]",
+        sp_model_kwargs: Optional[dict[str, Any]] = None,
+        **kwargs,
+    ) -> None:
+        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+
+        try:
+            import sentencepiece as spm
+        except ImportError:
+            logger.warning(
+                "You need to install SentencePiece to use XLMRobertaTokenizer: https://github.com/google/sentencepiece"
+                " pip install sentencepiece"
+            )
+            raise
+
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(str(vocab_file))
+        self.vocab_file = vocab_file
+
+        # Original fairseq vocab and spm vocab must be "aligned":
+        # Vocab    |    0    |    1    |   2    |    3    |  4  |  5  |  6  |   7   |   8   |  9
+        # -------- | ------- | ------- | ------ | ------- | --- | --- | --- | ----- | ----- | ----
+        # fairseq  | '<s>'   | '<pad>' | '</s>' | '<unk>' | ',' | '.' | '▁' | 's'   | '▁de' | '-'
+        # spm      | '<unk>' | '<s>'   | '</s>' | ','     | '.' | '▁' | 's' | '▁de' | '-'   | '▁a'
+
+        # put special tokens and [unused] tokens into the vocab
+        self.fairseq_tokens_to_ids = {"[PAD]": 0, "[CLS]": 1, "[SEP]": 2, "[UNK]": 3, "[MASK]": 4}
+
+        for i in range(10):
+            tok = f"[unused{i}]"
+            self.fairseq_tokens_to_ids[tok] = 5 + i
+
+        # The first "real" token "," has position 15 in the embedding vocab and position 3 in the spm vocab
+        self.fairseq_offset = 12
+        self.fairseq_ids_to_tokens = {v: k for k, v in self.fairseq_tokens_to_ids.items()}
+
+        # TODO ArthurZ fairseq_ids_to_tokens should be removed
+
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            sep_token=sep_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            cls_token=cls_token,
+            mask_token=mask_token,
+            sp_model_kwargs=self.sp_model_kwargs,
+            **kwargs,
+        )
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        state["sp_model"] = None
+        return state
+
+    def __setstate__(self, d):
+        self.__dict__ = d
+        try:
+            import sentencepiece as spm
+        except ImportError:
+            logger.warning(
+                "You need to install SentencePiece to use XLMRobertaTokenizer: https://github.com/google/sentencepiece"
+                " pip install sentencepiece"
+            )
+            raise
+
+        # for backward compatibility
+        if not hasattr(self, "sp_model_kwargs"):
+            self.sp_model_kwargs = {}
+
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(self.vocab_file)
+
+    def get_special_tokens_mask(
+        self, token_ids_0: list[int], token_ids_1: Optional[list[int]] = None, already_has_special_tokens: bool = False
+    ) -> list[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`list[int]`):
+                List of IDs.
+            token_ids_1 (`list[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `list[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        if token_ids_1 is None:
+            return ([0] * len(token_ids_0)) + [1]
+        return ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: list[int], token_ids_1: Optional[list[int]] = None
+    ) -> list[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. XLMProphetNet
+        does not make use of token type ids, therefore a list of zeros is returned.
+
+        Args:
+            token_ids_0 (`list[int]`):
+                List of IDs.
+            token_ids_1 (`list[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `list[int]`: List of zeros.
+
+        """
+
+        sep = [self.sep_token_id]
+
+        if token_ids_1 is None:
+            return len(token_ids_0 + sep) * [0]
+        return len(token_ids_0 + sep + sep + token_ids_1 + sep) * [0]
+
+    @property
+    def vocab_size(self):
+        return len(self.sp_model) + self.fairseq_offset
+
+    def get_vocab(self):
+        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def _tokenize(self, text: str) -> str:
+        return self.sp_model.encode(text, out_type=str)
+
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        if token in self.fairseq_tokens_to_ids:
+            return self.fairseq_tokens_to_ids[token]
+        spm_id = self.sp_model.PieceToId(token)
+
+        # Need to return unknown token if the SP model returned 0
+        return spm_id + self.fairseq_offset if spm_id else self.unk_token_id
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        if index in self.fairseq_ids_to_tokens:
+            return self.fairseq_ids_to_tokens[index]
+        return self.sp_model.IdToPiece(index - self.fairseq_offset)
+
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (strings for sub-words) in a single string."""
+        out_string = "".join(tokens).replace(SPIECE_UNDERLINE, " ").strip()
+        return out_string
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> tuple[str]:
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "wb") as fi:
+                content_spiece_model = self.sp_model.serialized_model_proto()
+                fi.write(content_spiece_model)
+
+        return (out_vocab_file,)
+
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: list[int], token_ids_1: Optional[list[int]] = None
+    ) -> list[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A XLMProphetNet sequence has the following format:
+
+        - single sequence: `X [SEP]`
+        - pair of sequences: `A [SEP] B [SEP]`
+
+        Args:
+            token_ids_0 (`list[int]`):
+                List of IDs to which the special tokens will be added
+            token_ids_1 (`list[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `list[int]`: list of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+
+        if token_ids_1 is None:
+            return token_ids_0 + [self.sep_token_id]
+        sep = [self.sep_token_id]
+        return token_ids_0 + sep + token_ids_1 + sep
+
+
+__all__ = ["XLMProphetNetTokenizer"]