Add QDQBert model and quantization examples of SQUAD task (#14066)

* clean up branch for add-qdqbert-model

* README update for QAT example; update docstrings in modeling_qdqbert.py

* Update qdqbert.rst

* Update README.md

* Update README.md

* calibration data using traning set; QAT example runs in fp32

* re-use BERTtokenizer for qdqbert

* Update docs/source/model_doc/qdqbert.rst
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update docs/source/model_doc/qdqbert.rst
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update docs/source/model_doc/qdqbert.rst
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* remove qdqbert tokenizer

* Update qdqbert.rst

* update evaluate-hf-trt-qa.py

* update configuration_qdqbert.py

* update modeling_qdqbert.py: add copied statement; replace assert with ValueError

* update copied from statement

* add is_quantization_available; run make fix-copies

* unittest add require_quantization

* add backend dependency to qdqbert model

* update README; update evaluate script; make style

* lint

* docs qdqbert update

* circleci build_doc add pytorch-quantization for qdqbert

* update README

* update example readme with instructions to upgrade TensorRT to 8.2

* Update src/transformers/models/qdqbert/configuration_qdqbert.py
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/models/qdqbert/configuration_qdqbert.py
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/models/qdqbert/configuration_qdqbert.py
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Update src/transformers/models/qdqbert/configuration_qdqbert.py
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* change quantization to pytorch_quantization for backend requirement

* feed_forward_chunking not supported in QDQBert

* make style

* update model docstrings and comments in testing scripts

* rename example to quantization-qdqbert; rename example scripts from qat to quant

* Update src/transformers/models/qdqbert/modeling_qdqbert.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* rm experimental functions in quant_trainer

* qa cleanup

* make fix-copies for docs index.rst

* fix doctree; use post_init() for qdqbert

* fix early device assignment for qdqbert

* fix CI:Model templates runner
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

src/transformers/models/qdqbert/__init__.py

+# flake8: noqa
+# There's no way to ignore "F401 '...' imported but unused" warnings in this
+# module, but to preserve other warnings. So, don't check this module at all.
+
+# Copyright 2021 NVIDIA Corporation and 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 ...file_utils import _LazyModule, is_torch_available
+
+
+_import_structure = {
+    "configuration_qdqbert": ["QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP", "QDQBertConfig"],
+}
+
+if is_torch_available():
+    _import_structure["modeling_qdqbert"] = [
+        "QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST",
+        "QDQBertForMaskedLM",
+        "QDQBertForMultipleChoice",
+        "QDQBertForNextSentencePrediction",
+        "QDQBertForQuestionAnswering",
+        "QDQBertForSequenceClassification",
+        "QDQBertForTokenClassification",
+        "QDQBertLayer",
+        "QDQBertLMHeadModel",
+        "QDQBertModel",
+        "QDQBertPreTrainedModel",
+        "load_tf_weights_in_qdqbert",
+    ]
+
+
+if TYPE_CHECKING:
+    from .configuration_qdqbert import QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP, QDQBertConfig
+
+    if is_torch_available():
+        from .modeling_qdqbert import (
+            QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST,
+            QDQBertForMaskedLM,
+            QDQBertForMultipleChoice,
+            QDQBertForNextSentencePrediction,
+            QDQBertForQuestionAnswering,
+            QDQBertForSequenceClassification,
+            QDQBertForTokenClassification,
+            QDQBertLayer,
+            QDQBertLMHeadModel,
+            QDQBertModel,
+            QDQBertPreTrainedModel,
+            load_tf_weights_in_qdqbert,
+        )
+
+
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(__name__, globals()["__file__"], _import_structure)

src/transformers/models/qdqbert/configuration_qdqbert.py

+# coding=utf-8
+# Copyright 2021 NVIDIA Corporation and 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.
+""" QDQBERT model configuration """
+
+from ...configuration_utils import PretrainedConfig
+from ...utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
+    "bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/config.json",
+    # QDQBERT models can be loaded from any BERT checkpoint, available at https://huggingface.co/models?filter=bert
+}
+
+
+class QDQBertConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a :class:`~transformers.QDQBertModel`. It is used to
+    instantiate an QDQBERT 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 BERT `bert-base-uncased
+    <https://huggingface.co/bert-base-uncased>`__ architecture.
+
+    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
+    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.
+
+
+    Args:
+        vocab_size (:obj:`int`, `optional`, defaults to 30522):
+            Vocabulary size of the QDQBERT model. Defines the number of different tokens that can be represented by the
+            :obj:`inputs_ids` passed when calling :class:`~transformers.QDQBertModel`.
+        hidden_size (:obj:`int`, `optional`, defaults to 768):
+            Dimension of the encoder layers and the pooler layer.
+        num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (:obj:`int`, `optional`, defaults to 12):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (:obj:`int`, `optional`, defaults to 3072):
+            Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        hidden_act (:obj:`str` or :obj:`function`, `optional`, defaults to :obj:`"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string,
+            :obj:`"gelu"`, :obj:`"relu"`, :obj:`"selu"` and :obj:`"gelu_new"` are supported.
+        hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
+            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
+            The dropout ratio for the attention probabilities.
+        max_position_embeddings (:obj:`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).
+        type_vocab_size (:obj:`int`, `optional`, defaults to 2):
+            The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.QDQBertModel`.
+        initializer_range (:obj:`float`, `optional`, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
+            The epsilon used by the layer normalization layers.
+        use_cache (:obj:`bool`, `optional`, defaults to :obj:`True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if ``config.is_decoder=True``.
+
+    Examples::
+
+        >>> from transformers import QDQBertModel, QDQBertConfig
+
+        >>> # Initializing a QDQBERT bert-base-uncased style configuration
+        >>> configuration = QDQBertConfig()
+
+        >>> # Initializing a model from the bert-base-uncased style configuration
+        >>> model = QDQBertModel(configuration)
+
+        >>> # Accessing the model configuration
+        >>> configuration = model.config
+    """
+    model_type = "qdqbert"
+
+    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,
+        use_cache=True,
+        is_encoder_decoder=False,
+        pad_token_id=1,
+        bos_token_id=0,
+        eos_token_id=2,
+        **kwargs
+    ):
+        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
+
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.intermediate_size = intermediate_size
+        self.hidden_act = hidden_act
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.initializer_range = initializer_range
+        self.type_vocab_size = type_vocab_size
+        self.layer_norm_eps = layer_norm_eps
+        self.use_cache = use_cache

src/transformers/testing_utils.py

@@ -39,6 +39,7 @@ from .file_utils import (
     is_onnx_available,
     is_pandas_available,
     is_pytesseract_available,
+    is_pytorch_quantization_available,
     is_rjieba_available,
     is_scatter_available,
     is_sentencepiece_available,
@@ -371,6 +372,17 @@ def require_scatter(test_case):
         return test_case
 
 
+def require_pytorch_quantization(test_case):
+    """
+    Decorator marking a test that requires PyTorch Quantization Toolkit. These tests are skipped when PyTorch
+    Quantization Toolkit isn't installed.
+    """
+    if not is_pytorch_quantization_available():
+        return unittest.skip("test requires PyTorch Quantization Toolkit")(test_case)
+    else:
+        return test_case
+
+
 def require_vision(test_case):
     """
     Decorator marking a test that requires the vision dependencies. These tests are skipped when torchaudio isn't

src/transformers/utils/dummy_pytorch_quantization_and_torch_objects.py

+# This file is autogenerated by the command `make fix-copies`, do not edit.
+from ..file_utils import requires_backends
+
+
+QDQBERT_PRETRAINED_MODEL_ARCHIVE_LIST = None
+
+
+class QDQBertForMaskedLM:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertForMultipleChoice:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertForNextSentencePrediction:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+
+class QDQBertForQuestionAnswering:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertForSequenceClassification:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertForTokenClassification:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertLayer:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+
+class QDQBertLMHeadModel:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertModel:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+class QDQBertPreTrainedModel:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["pytorch_quantization", "torch"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["pytorch_quantization", "torch"])
+
+
+def load_tf_weights_in_qdqbert(*args, **kwargs):
+    requires_backends(load_tf_weights_in_qdqbert, ["pytorch_quantization", "torch"])