Delete configuration_ldmbert.py

configuration_ldmbert.py

@@ -1,150 +0,0 @@
-# coding=utf-8
-# Copyright 2022 The Fairseq Authors and The HuggingFace Inc. 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.
-""" LDMBERT model configuration"""
-import warnings
-from collections import OrderedDict
-from typing import Any, Mapping, Optional
-
-from transformers import PreTrainedTokenizer
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import TensorType, is_torch_available, logging
-
-
-logger = logging.get_logger(__name__)
-
-LDMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "ldm-bert": "https://huggingface.co/ldm-bert/resolve/main/config.json",
-}
-
-
-class LDMBertConfig(PretrainedConfig):
-    r"""
-    This is the configuration class to store the configuration of a [`LDMBertModel`]. It is used to instantiate a
-    LDMBERT 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 LDMBERT
-    [facebook/ldmbert-large](https://huggingface.co/facebook/ldmbert-large) 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 50265):
-            Vocabulary size of the LDMBERT model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`LDMBertModel`] or [`TFLDMBertModel`].
-        d_model (`int`, *optional*, defaults to 1024):
-            Dimensionality of the layers and the pooler layer.
-        encoder_layers (`int`, *optional*, defaults to 12):
-            Number of encoder layers.
-        decoder_layers (`int`, *optional*, defaults to 12):
-            Number of decoder layers.
-        encoder_attention_heads (`int`, *optional*, defaults to 16):
-            Number of attention heads for each attention layer in the Transformer encoder.
-        decoder_attention_heads (`int`, *optional*, defaults to 16):
-            Number of attention heads for each attention layer in the Transformer decoder.
-        decoder_ffn_dim (`int`, *optional*, defaults to 4096):
-            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
-        encoder_ffn_dim (`int`, *optional*, defaults to 4096):
-            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
-        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.
-        dropout (`float`, *optional*, defaults to 0.1):
-            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
-        attention_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout ratio for the attention probabilities.
-        activation_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout ratio for activations inside the fully connected layer.
-        classifier_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout ratio for classifier.
-        max_position_embeddings (`int`, *optional*, defaults to 1024):
-            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.
-        encoder_layerdrop: (`float`, *optional*, defaults to 0.0):
-            The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
-            for more details.
-        decoder_layerdrop: (`float`, *optional*, defaults to 0.0):
-            The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
-            for more details.
-        scale_embedding (`bool`, *optional*, defaults to `False`):
-            Scale embeddings by diving by sqrt(d_model).
-        use_cache (`bool`, *optional*, defaults to `True`):
-            Whether or not the model should return the last key/values attentions (not used by all models).
-        num_labels: (`int`, *optional*, defaults to 3):
-            The number of labels to use in [`LDMBertForSequenceClassification`].
-        forced_eos_token_id (`int`, *optional*, defaults to 2):
-            The id of the token to force as the last generated token when `max_length` is reached. Usually set to
-            `eos_token_id`.
-
-    Example:
-
-    ```python
-    >>> from transformers import LDMBertModel, LDMBertConfig
-
-    >>> # Initializing a LDMBERT facebook/ldmbert-large style configuration
-    >>> configuration = LDMBertConfig()
-
-    >>> # Initializing a model from the facebook/ldmbert-large style configuration
-    >>> model = LDMBertModel(configuration)
-
-    >>> # Accessing the model configuration
-    >>> configuration = model.config
-    ```"""
-    model_type = "ldmbert"
-    keys_to_ignore_at_inference = ["past_key_values"]
-    attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}
-
-    def __init__(
-        self,
-        vocab_size=30522,
-        max_position_embeddings=77,
-        encoder_layers=32,
-        encoder_ffn_dim=5120,
-        encoder_attention_heads=8,
-        head_dim=64,
-        encoder_layerdrop=0.0,
-        activation_function="gelu",
-        d_model=1280,
-        dropout=0.1,
-        attention_dropout=0.0,
-        activation_dropout=0.0,
-        init_std=0.02,
-        classifier_dropout=0.0,
-        scale_embedding=False,
-        use_cache=True,
-        pad_token_id=0,
-        **kwargs
-    ):
-        self.vocab_size = vocab_size
-        self.max_position_embeddings = max_position_embeddings
-        self.d_model = d_model
-        self.encoder_ffn_dim = encoder_ffn_dim
-        self.encoder_layers = encoder_layers
-        self.encoder_attention_heads = encoder_attention_heads
-        self.head_dim = head_dim
-        self.dropout = dropout
-        self.attention_dropout = attention_dropout
-        self.activation_dropout = activation_dropout
-        self.activation_function = activation_function
-        self.init_std = init_std
-        self.encoder_layerdrop = encoder_layerdrop
-        self.classifier_dropout = classifier_dropout
-        self.use_cache = use_cache
-        self.num_hidden_layers = encoder_layers
-        self.scale_embedding = scale_embedding  # scale factor will be sqrt(d_model) if True
-
-        super().__init__(pad_token_id=pad_token_id, **kwargs)