medcat.components.addons.relation_extraction.ml_utils
=====================================================
.. py:module:: medcat.components.addons.relation_extraction.ml_utils
Attributes
----------
.. autoapisummary::
medcat.components.addons.relation_extraction.ml_utils.logger
Classes
-------
.. autoapisummary::
medcat.components.addons.relation_extraction.ml_utils.BaseTokenizerWrapper
medcat.components.addons.relation_extraction.ml_utils.ConfigRelCAT
Functions
---------
.. autoapisummary::
medcat.components.addons.relation_extraction.ml_utils.split_list_train_test_by_class
medcat.components.addons.relation_extraction.ml_utils.load_bin_file
medcat.components.addons.relation_extraction.ml_utils.save_bin_file
medcat.components.addons.relation_extraction.ml_utils.save_state
medcat.components.addons.relation_extraction.ml_utils.load_state
medcat.components.addons.relation_extraction.ml_utils.save_results
medcat.components.addons.relation_extraction.ml_utils.load_results
medcat.components.addons.relation_extraction.ml_utils.create_tokenizer_pretrain
medcat.components.addons.relation_extraction.ml_utils.create_dense_layers
medcat.components.addons.relation_extraction.ml_utils.get_annotation_schema_tag
Module Contents
---------------
.. py:class:: BaseTokenizerWrapper(hf_tokenizers=None, max_seq_length = None, add_special_tokens = False)
Bases: :py:obj:`transformers.PreTrainedTokenizerFast`
Base class for all fast tokenizers (wrapping HuggingFace tokenizers library).
Inherits from [`~tokenization_utils_base.PreTrainedTokenizerBase`].
Handles all the shared methods for tokenization and special tokens, as well as methods for
downloading/caching/loading pretrained tokenizers, as well as adding tokens to the vocabulary.
This class also contains the added tokens in a unified way on top of all tokenizers so we don't have to handle the
specific vocabulary augmentation methods of the various underlying dictionary structures (BPE, sentencepiece...).
.. py:attribute:: name
:value: 'base_tokenizer_wrapper_rel'
.. py:method:: __init__(hf_tokenizers=None, max_seq_length = None, add_special_tokens = False)
.. py:attribute:: hf_tokenizers
:value: None
.. py:attribute:: max_seq_length
:value: None
.. py:attribute:: _add_special_tokens
:value: False
.. py:method:: get_size()
.. py:method:: token_to_id(token)
.. py:method:: get_pad_id()
.. py:method:: __call__(text, truncation = True)
Main method to tokenize and prepare for the model one or several sequence(s) or one or several pair(s) of
sequences.
:param text: The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
:type text: `str`, `List[str]`, `List[List[str]]`, *optional*
:param text_pair: The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
:type text_pair: `str`, `List[str]`, `List[List[str]]`, *optional*
:param text_target: The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a
list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized),
you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
:type text_target: `str`, `List[str]`, `List[List[str]]`, *optional*
:param text_pair_target: The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a
list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized),
you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
:type text_pair_target: `str`, `List[str]`, `List[List[str]]`, *optional*
.. py:method:: save(dir_path)
.. py:method:: load(tokenizer_path, relcat_config, **kwargs)
:classmethod:
.. py:attribute:: _backends
:value: ['tokenizers']
.. py:attribute:: vocab_files_names
.. py:attribute:: slow_tokenizer_class
:type: transformers.tokenization_utils.PreTrainedTokenizer
:value: None
.. py:attribute:: add_prefix_space
.. py:attribute:: _tokenizer
.. py:attribute:: _decode_use_source_tokenizer
:value: False
.. py:property:: is_fast
:type: bool
.. py:property:: can_save_slow_tokenizer
:type: bool
Whether or not the slow tokenizer can be saved. Usually for sentencepiece based slow tokenizer, this
can only be `True` if the original `"sentencepiece.model"` was not deleted.
:type: `bool`
.. py:property:: vocab_size
:type: int
Size of the base vocabulary (without the added tokens).
:type: `int`
.. py:method:: get_vocab()
Returns the vocabulary as a dictionary of token to index.
`tokenizer.get_vocab()[token]` is equivalent to `tokenizer.convert_tokens_to_ids(token)` when `token` is in the
vocab.
:Returns: **`Dict[str, int]`** -- The vocabulary.
.. py:property:: vocab
:type: Dict[str, int]
.. py:property:: added_tokens_encoder
:type: Dict[str, int]
Returns the sorted mapping from string to index. The added tokens encoder is cached for performance
optimisation in `self._added_tokens_encoder` for the slow tokenizers.
.. py:property:: added_tokens_decoder
:type: Dict[int, transformers.tokenization_utils_base.AddedToken]
Returns the added tokens in the vocabulary as a dictionary of index to AddedToken.
:Returns: **`Dict[str, int]`** -- The added tokens.
.. py:method:: get_added_vocab()
Returns the added tokens in the vocabulary as a dictionary of token to index.
:Returns: **`Dict[str, int]`** -- The added tokens.
.. py:method:: __len__()
Size of the full vocabulary with the added tokens.
.. py:property:: backend_tokenizer
:type: tokenizers.Tokenizer
The Rust tokenizer used as a backend.
:type: `tokenizers.implementations.BaseTokenizer`
.. py:property:: decoder
:type: tokenizers.decoders.Decoder
The Rust decoder for this tokenizer.
:type: `tokenizers.decoders.Decoder`
.. py:method:: _convert_encoding(encoding, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True)
Convert the encoding representation (from low-level HuggingFace tokenizer output) to a python Dict and a list
of encodings, take care of building a batch from overflowing tokens.
Overflowing tokens are converted to additional examples (like batches) so the output values of the dict are
lists (overflows) of lists (tokens).
Output shape: (overflows, sequence length)
.. py:method:: convert_tokens_to_ids(tokens)
Converts a token string (or a sequence of tokens) in a single integer id (or a Iterable of ids), using the
vocabulary.
:param tokens: One or several token(s) to convert to token id(s).
:type tokens: `str` or `Iterable[str]`
:Returns: **`int` or `List[int]`** -- The token id or list of token ids.
.. py:method:: _convert_token_to_id_with_added_voc(token)
.. py:method:: _convert_id_to_token(index)
.. py:method:: _add_tokens(new_tokens, special_tokens=False)
.. py:method:: num_special_tokens_to_add(pair = False)
Returns the number of added tokens when encoding a sequence with special tokens.
This encodes a dummy input and checks the number of added tokens, and is therefore not efficient. Do not put
this inside your training loop.
:param pair: Whether the number of added tokens should be computed in the case of a sequence pair or a single
sequence.
:type pair: `bool`, *optional*, defaults to `False`
:Returns: **`int`** -- Number of special tokens added to sequences.
.. py:method:: convert_ids_to_tokens(ids, skip_special_tokens = False)
Converts a single index or a sequence of indices in a token or a sequence of tokens, using the vocabulary and
added tokens.
:param ids: The token id (or token ids) to convert to tokens.
:type ids: `int` or `List[int]`
:param skip_special_tokens: Whether or not to remove special tokens in the decoding.
:type skip_special_tokens: `bool`, *optional*, defaults to `False`
:Returns: **`str` or `List[str]`** -- The decoded token(s).
.. py:method:: tokenize(text, pair = None, add_special_tokens = False, **kwargs)
Converts a string into a sequence of tokens, replacing unknown tokens with the `unk_token`.
:param text: The sequence to be encoded.
:type text: `str`
:param pair: A second sequence to be encoded with the first.
:type pair: `str`, *optional*
:param add_special_tokens: Whether or not to add the special tokens associated with the corresponding model.
:type add_special_tokens: `bool`, *optional*, defaults to `False`
:param kwargs: Will be passed to the underlying model specific encode method. See details in
[`~PreTrainedTokenizerBase.__call__`]
:type kwargs: additional keyword arguments, *optional*
:Returns: **`List[str]`** -- The list of tokens.
.. py:method:: set_truncation_and_padding(padding_strategy, truncation_strategy, max_length, stride, pad_to_multiple_of, padding_side)
Define the truncation and the padding strategies for fast tokenizers (provided by HuggingFace tokenizers
library) and restore the tokenizer settings afterwards.
The provided tokenizer has no padding / truncation strategy before the managed section. If your tokenizer set a
padding / truncation strategy before, then it will be reset to no padding / truncation when exiting the managed
section.
:param padding_strategy: The kind of padding that will be applied to the input
:type padding_strategy: [`~utils.PaddingStrategy`]
:param truncation_strategy: The kind of truncation that will be applied to the input
:type truncation_strategy: [`~tokenization_utils_base.TruncationStrategy`]
:param max_length: The maximum size of a sequence.
:type max_length: `int`
:param stride: The stride to use when handling overflow.
:type stride: `int`
:param pad_to_multiple_of: If set will pad the sequence to a multiple of the provided value. This is especially useful to enable
the use of Tensor Cores on NVIDIA hardware with compute capability `>= 7.5` (Volta).
:type pad_to_multiple_of: `int`, *optional*
:param padding_side: The side on which the model should have padding applied. Should be selected between ['right', 'left'].
Default value is picked from the class attribute of the same name.
:type padding_side: `str`, *optional*
.. py:method:: _batch_encode_plus(batch_text_or_text_pairs, add_special_tokens = True, padding_strategy = PaddingStrategy.DO_NOT_PAD, truncation_strategy = TruncationStrategy.DO_NOT_TRUNCATE, max_length = None, stride = 0, is_split_into_words = False, pad_to_multiple_of = None, padding_side = None, return_tensors = None, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True, split_special_tokens = False)
.. py:method:: _encode_plus(text, text_pair = None, add_special_tokens = True, padding_strategy = PaddingStrategy.DO_NOT_PAD, truncation_strategy = TruncationStrategy.DO_NOT_TRUNCATE, max_length = None, stride = 0, is_split_into_words = False, pad_to_multiple_of = None, padding_side = None, return_tensors = None, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True, split_special_tokens = False, **kwargs)
.. py:method:: convert_tokens_to_string(tokens)
Converts a sequence of tokens in a single string. The most simple way to do it is `" ".join(tokens)` but we
often want to remove sub-word tokenization artifacts at the same time.
:param tokens: The token to join in a string.
:type tokens: `List[str]`
:Returns: **`str`** -- The joined tokens.
.. py:method:: _decode(token_ids, skip_special_tokens = False, clean_up_tokenization_spaces = None, **kwargs)
.. py:method:: _save_pretrained(save_directory, file_names, legacy_format = None, filename_prefix = None)
Save a tokenizer using the slow-tokenizer/legacy format: vocabulary + added tokens as well as in a unique JSON
file containing {config + vocab + added-tokens}.
.. py:method:: train_new_from_iterator(text_iterator, vocab_size, length=None, new_special_tokens=None, special_tokens_map=None, **kwargs)
Trains a tokenizer on a new corpus with the same defaults (in terms of special tokens or tokenization pipeline)
as the current one.
:param text_iterator: The training corpus. Should be a generator of batches of texts, for instance a list of lists of texts
if you have everything in memory.
:type text_iterator: generator of `List[str]`
:param vocab_size: The size of the vocabulary you want for your tokenizer.
:type vocab_size: `int`
:param length: The total number of sequences in the iterator. This is used to provide meaningful progress tracking
:type length: `int`, *optional*
:param new_special_tokens: A list of new special tokens to add to the tokenizer you are training.
:type new_special_tokens: list of `str` or `AddedToken`, *optional*
:param special_tokens_map: If you want to rename some of the special tokens this tokenizer uses, pass along a mapping old special
token name to new special token name in this argument.
:type special_tokens_map: `Dict[str, str]`, *optional*
:param kwargs: Additional keyword arguments passed along to the trainer from the 🤗 Tokenizers library.
:type kwargs: `Dict[str, Any]`, *optional*
:Returns: * **[`PreTrainedTokenizerFast`]** -- A new tokenizer of the same type as the original one, trained on
* **`text_iterator`.**
.. py:attribute:: pretrained_vocab_files_map
:type: Dict[str, Dict[str, str]]
.. py:attribute:: _auto_class
:type: Optional[str]
:value: None
.. py:attribute:: model_input_names
:type: List[str]
:value: ['input_ids', 'token_type_ids', 'attention_mask']
.. py:attribute:: padding_side
:type: str
:value: 'right'
.. py:attribute:: truncation_side
:type: str
:value: 'right'
.. py:attribute:: init_inputs
:value: ()
.. py:attribute:: init_kwargs
.. py:attribute:: name_or_path
.. py:attribute:: _processor_class
.. py:attribute:: model_max_length
.. py:attribute:: clean_up_tokenization_spaces
.. py:attribute:: split_special_tokens
.. py:attribute:: deprecation_warnings
.. py:attribute:: _in_target_context_manager
:value: False
.. py:attribute:: chat_template
.. py:attribute:: extra_special_tokens
.. py:property:: max_len_single_sentence
:type: int
The maximum length of a sentence that can be fed to the model.
:type: `int`
.. py:property:: max_len_sentences_pair
:type: int
The maximum combined length of a pair of sentences that can be fed to the model.
:type: `int`
.. py:method:: _set_processor_class(processor_class)
Sets processor class as an attribute.
.. py:method:: __repr__()
.. py:method:: apply_chat_template(conversation, tools = None, documents = None, chat_template = None, add_generation_prompt = False, continue_final_message = False, tokenize = True, padding = False, truncation = False, max_length = None, return_tensors = None, return_dict = False, return_assistant_tokens_mask = False, tokenizer_kwargs = None, **kwargs)
Converts a list of dictionaries with `"role"` and `"content"` keys to a list of token
ids. This method is intended for use with chat models, and will read the tokenizer's chat_template attribute to
determine the format and control tokens to use when converting.
:param conversation: A list of dicts
with "role" and "content" keys, representing the chat history so far.
:type conversation: Union[List[Dict[str, str]], List[List[Dict[str, str]]]]
:param tools: A list of tools (callable functions) that will be accessible to the model. If the template does not
support function calling, this argument will have no effect. Each tool should be passed as a JSON Schema,
giving the name, description and argument types for the tool. See our
[chat templating guide](https://huggingface.co/docs/transformers/main/en/chat_templating#automated-function-conversion-for-tool-use)
for more information.
:type tools: `List[Dict]`, *optional*
:param documents: A list of dicts representing documents that will be accessible to the model if it is performing RAG
(retrieval-augmented generation). If the template does not support RAG, this argument will have no
effect. We recommend that each document should be a dict containing "title" and "text" keys. Please
see the RAG section of the [chat templating guide](https://huggingface.co/docs/transformers/main/en/chat_templating#arguments-for-RAG)
for examples of passing documents with chat templates.
:type documents: `List[Dict[str, str]]`, *optional*
:param chat_template: A Jinja template to use for this conversion. It is usually not necessary to pass anything to this
argument, as the model's template will be used by default.
:type chat_template: `str`, *optional*
:param add_generation_prompt: If this is set, a prompt with the token(s) that indicate
the start of an assistant message will be appended to the formatted output. This is useful when you want to generate a response from the model.
Note that this argument will be passed to the chat template, and so it must be supported in the
template for this argument to have any effect.
:type add_generation_prompt: bool, *optional*
:param continue_final_message: If this is set, the chat will be formatted so that the final
message in the chat is open-ended, without any EOS tokens. The model will continue this message
rather than starting a new one. This allows you to "prefill" part of
the model's response for it. Cannot be used at the same time as `add_generation_prompt`.
:type continue_final_message: bool, *optional*
:param tokenize: Whether to tokenize the output. If `False`, the output will be a string.
:type tokenize: `bool`, defaults to `True`
:param padding: Whether to pad sequences to the maximum length. Has no effect if tokenize is `False`.
:type padding: `bool`, defaults to `False`
:param truncation: Whether to truncate sequences at the maximum length. Has no effect if tokenize is `False`.
:type truncation: `bool`, defaults to `False`
:param max_length: Maximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is `False`. If
not specified, the tokenizer's `max_length` attribute will be used as a default.
:type max_length: `int`, *optional*
:param return_tensors: If set, will return tensors of a particular framework. Has no effect if tokenize is `False`. Acceptable
values are:
- `'tf'`: Return TensorFlow `tf.Tensor` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return NumPy `np.ndarray` objects.
- `'jax'`: Return JAX `jnp.ndarray` objects.
:type return_tensors: `str` or [`~utils.TensorType`], *optional*
:param return_dict: Whether to return a dictionary with named outputs. Has no effect if tokenize is `False`.
:type return_dict: `bool`, defaults to `False`
:param tokenizer_kwargs (`Dict[str: Any]`, *optional*): Additional kwargs to pass to the tokenizer.
:param return_assistant_tokens_mask: Whether to return a mask of the assistant generated tokens. For tokens generated by the assistant,
the mask will contain 1. For user and system tokens, the mask will contain 0.
This functionality is only available for chat templates that support it via the `{% generation %}` keyword.
:type return_assistant_tokens_mask: `bool`, defaults to `False`
:param \*\*kwargs: Additional kwargs to pass to the template renderer. Will be accessible by the chat template.
:Returns: * **`Union[List[int], Dict]`** -- A list of token ids representing the tokenized chat so far, including control tokens. This
* **output is ready to pass to the model, either directly or via methods like `generate()`. If `return_dict` is**
* **set, will return a dict of tokenizer outputs instead.**
.. py:method:: get_chat_template(chat_template = None, tools = None)
Retrieve the chat template string used for tokenizing chat messages. This template is used
internally by the `apply_chat_template` method and can also be used externally to retrieve the model's chat
template for better generation tracking.
:param chat_template: A Jinja template or the name of a template to use for this conversion.
It is usually not necessary to pass anything to this argument,
as the model's template will be used by default.
:type chat_template: `str`, *optional*
:param tools: A list of tools (callable functions) that will be accessible to the model. If the template does not
support function calling, this argument will have no effect. Each tool should be passed as a JSON Schema,
giving the name, description and argument types for the tool. See our
[chat templating guide](https://huggingface.co/docs/transformers/main/en/chat_templating#automated-function-conversion-for-tool-use)
for more information.
:type tools: `List[Dict]`, *optional*
:Returns: **`str`** -- The chat template string.
.. py:method:: from_pretrained(pretrained_model_name_or_path, *init_inputs, cache_dir = None, force_download = False, local_files_only = False, token = None, revision = 'main', trust_remote_code=False, **kwargs)
:classmethod:
Instantiate a [`~tokenization_utils_base.PreTrainedTokenizerBase`] (or a derived class) from a predefined
tokenizer.
:param pretrained_model_name_or_path: Can be either:
- A string, the *model id* of a predefined tokenizer hosted inside a model repo on huggingface.co.
- A path to a *directory* containing vocabulary files required by the tokenizer, for instance saved
using the [`~tokenization_utils_base.PreTrainedTokenizerBase.save_pretrained`] method, e.g.,
`./my_model_directory/`.
- (**Deprecated**, not applicable to all derived classes) A path or url to a single saved vocabulary
file (if and only if the tokenizer only requires a single vocabulary file like Bert or XLNet), e.g.,
`./my_model_directory/vocab.txt`.
:type pretrained_model_name_or_path: `str` or `os.PathLike`
:param cache_dir: Path to a directory in which a downloaded predefined tokenizer vocabulary files should be cached if the
standard cache should not be used.
:type cache_dir: `str` or `os.PathLike`, *optional*
:param force_download: Whether or not to force the (re-)download the vocabulary files and override the cached versions if they
exist.
:type force_download: `bool`, *optional*, defaults to `False`
:param resume_download: Deprecated and ignored. All downloads are now resumed by default when possible.
Will be removed in v5 of Transformers.
:param proxies: A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
:type proxies: `Dict[str, str]`, *optional*
:param token: The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
when running `huggingface-cli login` (stored in `~/.huggingface`).
:type token: `str` or *bool*, *optional*
:param local_files_only: Whether or not to only rely on local files and not to attempt to download any files.
:type local_files_only: `bool`, *optional*, defaults to `False`
:param revision: The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
identifier allowed by git.
:type revision: `str`, *optional*, defaults to `"main"`
:param subfolder: In case the relevant files are located inside a subfolder of the model repo on huggingface.co (e.g. for
facebook/rag-token-base), specify it here.
:type subfolder: `str`, *optional*
:param inputs: Will be passed along to the Tokenizer `__init__` method.
:type inputs: additional positional arguments, *optional*
:param trust_remote_code: Whether or not to allow for custom models defined on the Hub in their own modeling files. This option
should only be set to `True` for repositories you trust and in which you have read the code, as it will
execute code present on the Hub on your local machine.
:type trust_remote_code: `bool`, *optional*, defaults to `False`
:param kwargs: Will be passed to the Tokenizer `__init__` method. Can be used to set special tokens like `bos_token`,
`eos_token`, `unk_token`, `sep_token`, `pad_token`, `cls_token`, `mask_token`,
`additional_special_tokens`. See parameters in the `__init__` for more details.
:type kwargs: additional keyword arguments, *optional*
Passing `token=True` is required when you want to use a private model.
Examples:
```python
# We can't instantiate directly the base class *PreTrainedTokenizerBase* so let's show our examples on a derived class: BertTokenizer
# Download vocabulary from huggingface.co and cache.
tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased")
# Download vocabulary from huggingface.co (user-uploaded) and cache.
tokenizer = BertTokenizer.from_pretrained("dbmdz/bert-base-german-cased")
# If vocabulary files are in a directory (e.g. tokenizer was saved using *save_pretrained('./test/saved_model/')*)
tokenizer = BertTokenizer.from_pretrained("./test/saved_model/")
# If the tokenizer uses a single vocabulary file, you can point directly to this file
tokenizer = BertTokenizer.from_pretrained("./test/saved_model/my_vocab.txt")
# You can link tokens to special vocabulary when instantiating
tokenizer = BertTokenizer.from_pretrained("google-bert/bert-base-uncased", unk_token="")
# You should be sure '' is in the vocabulary when doing that.
# Otherwise use tokenizer.add_special_tokens({'unk_token': ''}) instead)
assert tokenizer.unk_token == ""
```
.. py:method:: _from_pretrained(resolved_vocab_files, pretrained_model_name_or_path, init_configuration, *init_inputs, token=None, cache_dir=None, local_files_only=False, _commit_hash=None, _is_local=False, trust_remote_code=False, **kwargs)
:classmethod:
.. py:method:: _eventually_correct_t5_max_length(pretrained_model_name_or_path, max_model_length, init_max_model_length)
:staticmethod:
.. py:method:: convert_added_tokens(obj, save=False, add_type_field=True)
:classmethod:
.. py:method:: save_pretrained(save_directory, legacy_format = None, filename_prefix = None, push_to_hub = False, **kwargs)
Save the full tokenizer state.
This method make sure the full tokenizer can then be re-loaded using the
[`~tokenization_utils_base.PreTrainedTokenizer.from_pretrained`] class method..
Warning,None This won't save modifications you may have applied to the tokenizer after the instantiation (for
instance, modifying `tokenizer.do_lower_case` after creation).
:param save_directory: The path to a directory where the tokenizer will be saved.
:type save_directory: `str` or `os.PathLike`
:param legacy_format: Only applicable for a fast tokenizer. If unset (default), will save the tokenizer in the unified JSON
format as well as in legacy format if it exists, i.e. with tokenizer specific vocabulary and a separate
added_tokens files.
If `False`, will only save the tokenizer in the unified JSON format. This format is incompatible with
"slow" tokenizers (not powered by the *tokenizers* library), so the tokenizer will not be able to be
loaded in the corresponding "slow" tokenizer.
If `True`, will save the tokenizer in legacy format. If the "slow" tokenizer doesn't exits, a value
error is raised.
:type legacy_format: `bool`, *optional*
:param filename_prefix: A prefix to add to the names of the files saved by the tokenizer.
:type filename_prefix: `str`, *optional*
:param push_to_hub: Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
namespace).
:type push_to_hub: `bool`, *optional*, defaults to `False`
:param kwargs: Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
:type kwargs: `Dict[str, Any]`, *optional*
:Returns: **A tuple of `str`** -- The files saved.
.. py:method:: save_vocabulary(save_directory, filename_prefix = None)
:abstractmethod:
Save only the vocabulary of the tokenizer (vocabulary + added tokens).
This method won't save the configuration and special token mappings of the tokenizer. Use
[`~PreTrainedTokenizerFast._save_pretrained`] to save the whole state of the tokenizer.
:param save_directory: The directory in which to save the vocabulary.
:type save_directory: `str`
:param filename_prefix: An optional prefix to add to the named of the saved files.
:type filename_prefix: `str`, *optional*
:Returns: **`Tuple** (*str*) -- Paths to the files saved.
.. py:method:: encode(text, text_pair = None, add_special_tokens = True, padding = False, truncation = None, max_length = None, stride = 0, padding_side = None, return_tensors = None, **kwargs)
Converts a string to a sequence of ids (integer), using the tokenizer and vocabulary.
Same as doing `self.convert_tokens_to_ids(self.tokenize(text))`.
:param text: The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the
`tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
method).
:type text: `str`, `List[str]` or `List[int]`
:param text_pair: Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using
the `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
method).
:type text_pair: `str`, `List[str]` or `List[int]`, *optional*
.. py:method:: _get_padding_truncation_strategies(padding=False, truncation=None, max_length=None, pad_to_multiple_of=None, verbose=True, **kwargs)
Find the correct padding/truncation strategy with backward compatibility for old arguments (truncation_strategy
and pad_to_max_length) and behaviors.
.. py:method:: _call_one(text, text_pair = None, add_special_tokens = True, padding = False, truncation = None, max_length = None, stride = 0, is_split_into_words = False, pad_to_multiple_of = None, padding_side = None, return_tensors = None, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True, split_special_tokens = False, **kwargs)
.. py:method:: encode_plus(text, text_pair = None, add_special_tokens = True, padding = False, truncation = None, max_length = None, stride = 0, is_split_into_words = False, pad_to_multiple_of = None, padding_side = None, return_tensors = None, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True, **kwargs)
Tokenize and prepare for the model a sequence or a pair of sequences.
This method is deprecated, `__call__` should be used instead.
:param text: The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the
`tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
method).
:type text: `str`, `List[str]` or (for non-fast tokenizers) `List[int]`
:param text_pair: Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using
the `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
method).
:type text_pair: `str`, `List[str]` or `List[int]`, *optional*
.. py:method:: batch_encode_plus(batch_text_or_text_pairs, add_special_tokens = True, padding = False, truncation = None, max_length = None, stride = 0, is_split_into_words = False, pad_to_multiple_of = None, padding_side = None, return_tensors = None, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True, split_special_tokens = False, **kwargs)
Tokenize and prepare for the model a list of sequences or a list of pairs of sequences.
This method is deprecated, `__call__` should be used instead.
:param batch_text_or_text_pairs: Batch of sequences or pair of sequences to be encoded. This can be a list of
string/string-sequences/int-sequences or a list of pair of string/string-sequences/int-sequence (see
details in `encode_plus`).
:type batch_text_or_text_pairs: `List[str]`, `List[Tuple[str, str]]`, `List[List[str]]`, `List[Tuple[List[str], List[str]]]`, and for not-fast tokenizers, also `List[List[int]]`, `List[Tuple[List[int], List[int]]]`
.. py:method:: pad(encoded_inputs, padding = True, max_length = None, pad_to_multiple_of = None, padding_side = None, return_attention_mask = None, return_tensors = None, verbose = True)
Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length
in the batch.
Padding side (left/right) padding token ids are defined at the tokenizer level (with `self.padding_side`,
`self.pad_token_id` and `self.pad_token_type_id`).
Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the
text followed by a call to the `pad` method to get a padded encoding.
If the `encoded_inputs` passed are dictionary of numpy arrays, PyTorch tensors or TensorFlow tensors, the
result will use the same type unless you provide a different tensor type with `return_tensors`. In the case of
PyTorch tensors, you will lose the specific device of your tensors however.
:param encoded_inputs: Tokenized inputs. Can represent one input ([`BatchEncoding`] or `Dict[str, List[int]]`) or a batch of
tokenized inputs (list of [`BatchEncoding`], *Dict[str, List[List[int]]]* or *List[Dict[str,
List[int]]]*) so you can use this method during preprocessing as well as in a PyTorch Dataloader
collate function.
Instead of `List[int]` you can have tensors (numpy arrays, PyTorch tensors or TensorFlow tensors), see
the note above for the return type.
:type encoded_inputs: [`BatchEncoding`], list of [`BatchEncoding`], `Dict[str, List[int]]`, `Dict[str, List[List[int]]` or `List[Dict[str, List[int]]]`
:param padding: Select a strategy to pad the returned sequences (according to the model's padding side and padding
index) among:
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
sequence if provided).
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
acceptable input length for the model if that argument is not provided.
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
lengths).
:type padding: `bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`
:param max_length: Maximum length of the returned list and optionally padding length (see above).
:type max_length: `int`, *optional*
:param pad_to_multiple_of: If set will pad the sequence to a multiple of the provided value.
This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability
`>= 7.5` (Volta).
:type pad_to_multiple_of: `int`, *optional*
:param padding_side: The side on which the model should have padding applied. Should be selected between ['right', 'left'].
Default value is picked from the class attribute of the same name.
:type padding_side: `str`, *optional*
:param return_attention_mask: Whether to return the attention mask. If left to the default, will return the attention mask according
to the specific tokenizer's default, defined by the `return_outputs` attribute.
[What are attention masks?](../glossary#attention-mask)
:type return_attention_mask: `bool`, *optional*
:param return_tensors: If set, will return tensors instead of list of python integers. Acceptable values are:
- `'tf'`: Return TensorFlow `tf.constant` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return Numpy `np.ndarray` objects.
:type return_tensors: `str` or [`~utils.TensorType`], *optional*
:param verbose: Whether or not to print more information and warnings.
:type verbose: `bool`, *optional*, defaults to `True`
.. py:method:: create_token_type_ids_from_sequences(token_ids_0, token_ids_1 = None)
Create the token type IDs corresponding to the sequences passed. [What are token type
IDs?](../glossary#token-type-ids)
Should be overridden in a subclass if the model has a special way of building those.
:param token_ids_0: The first tokenized sequence.
:type token_ids_0: `List[int]`
:param token_ids_1: The second tokenized sequence.
:type token_ids_1: `List[int]`, *optional*
:Returns: **`List[int]`** -- The token type ids.
.. py:method:: build_inputs_with_special_tokens(token_ids_0, token_ids_1 = None)
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens.
This implementation does not add special tokens and this method should be overridden in a subclass.
:param token_ids_0: The first tokenized sequence.
:type token_ids_0: `List[int]`
:param token_ids_1: The second tokenized sequence.
:type token_ids_1: `List[int]`, *optional*
:Returns: **`List[int]`** -- The model input with special tokens.
.. py:method:: prepare_for_model(ids, pair_ids = None, add_special_tokens = True, padding = False, truncation = None, max_length = None, stride = 0, pad_to_multiple_of = None, padding_side = None, return_tensors = None, return_token_type_ids = None, return_attention_mask = None, return_overflowing_tokens = False, return_special_tokens_mask = False, return_offsets_mapping = False, return_length = False, verbose = True, prepend_batch_axis = False, **kwargs)
Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It
adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
manages a moving window (with user defined stride) for overflowing tokens. Please Note, for *pair_ids*
different than `None` and *truncation_strategy = longest_first* or `True`, it is not possible to return
overflowing tokens. Such a combination of arguments will raise an error.
:param ids: Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
`convert_tokens_to_ids` methods.
:type ids: `List[int]`
:param pair_ids: Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
and `convert_tokens_to_ids` methods.
:type pair_ids: `List[int]`, *optional*
.. py:method:: truncate_sequences(ids, pair_ids = None, num_tokens_to_remove = 0, truncation_strategy = 'longest_first', stride = 0)
Truncates a sequence pair in-place following the strategy.
:param ids: Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
`convert_tokens_to_ids` methods.
:type ids: `List[int]`
:param pair_ids: Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
and `convert_tokens_to_ids` methods.
:type pair_ids: `List[int]`, *optional*
:param num_tokens_to_remove: Number of tokens to remove using the truncation strategy.
:type num_tokens_to_remove: `int`, *optional*, defaults to 0
:param truncation_strategy: The strategy to follow for truncation. Can be:
- `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
maximum acceptable input length for the model if that argument is not provided. This will truncate
token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a
batch of pairs) is provided.
- `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
maximum acceptable input length for the model if that argument is not provided. This will only
truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
- `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the
maximum acceptable input length for the model if that argument is not provided. This will only
truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
- `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths greater
than the model maximum admissible input size).
:type truncation_strategy: `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `'longest_first'`
:param stride: If set to a positive number, the overflowing tokens returned will contain some tokens from the main
sequence returned. The value of this argument defines the number of additional tokens.
:type stride: `int`, *optional*, defaults to 0
:Returns: * **`Tuple[List[int], List[int], List[int]]`** -- The truncated `ids`, the truncated `pair_ids` and the list of
* **overflowing tokens. Note** -- The *longest_first* strategy returns empty list of overflowing tokens if a pair
* **of sequences** (*or a batch of pairs*)
.. py:method:: _pad(encoded_inputs, max_length = None, padding_strategy = PaddingStrategy.DO_NOT_PAD, pad_to_multiple_of = None, padding_side = None, return_attention_mask = None)
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
:param encoded_inputs: Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
:param max_length: maximum length of the returned list and optionally padding length (see below).
Will truncate by taking into account the special tokens.
:param padding_strategy: PaddingStrategy to use for padding.
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
- PaddingStrategy.DO_NOT_PAD: Do not pad
The tokenizer padding sides are defined in `padding_side` argument:
- 'left': pads on the left of the sequences
- 'right': pads on the right of the sequences
:param pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
`>= 7.5` (Volta).
:param padding_side: The side on which the model should have padding applied. Should be selected between ['right', 'left'].
Default value is picked from the class attribute of the same name.
:param return_attention_mask: (optional) Set to False to avoid returning attention mask (default: set to model specifics)
.. py:method:: batch_decode(sequences, skip_special_tokens = False, clean_up_tokenization_spaces = None, **kwargs)
Convert a list of lists of token ids into a list of strings by calling decode.
:param sequences: List of tokenized input ids. Can be obtained using the `__call__` method.
:type sequences: `Union[List[int], List[List[int]], np.ndarray, torch.Tensor, tf.Tensor]`
:param skip_special_tokens: Whether or not to remove special tokens in the decoding.
:type skip_special_tokens: `bool`, *optional*, defaults to `False`
:param clean_up_tokenization_spaces: Whether or not to clean up the tokenization spaces. If `None`, will default to
`self.clean_up_tokenization_spaces`.
:type clean_up_tokenization_spaces: `bool`, *optional*
:param kwargs: Will be passed to the underlying model specific decode method.
:type kwargs: additional keyword arguments, *optional*
:Returns: **`List[str]`** -- The list of decoded sentences.
.. py:method:: decode(token_ids, skip_special_tokens = False, clean_up_tokenization_spaces = None, **kwargs)
Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special
tokens and clean up tokenization spaces.
Similar to doing `self.convert_tokens_to_string(self.convert_ids_to_tokens(token_ids))`.
:param token_ids: List of tokenized input ids. Can be obtained using the `__call__` method.
:type token_ids: `Union[int, List[int], np.ndarray, torch.Tensor, tf.Tensor]`
:param skip_special_tokens: Whether or not to remove special tokens in the decoding.
:type skip_special_tokens: `bool`, *optional*, defaults to `False`
:param clean_up_tokenization_spaces: Whether or not to clean up the tokenization spaces. If `None`, will default to
`self.clean_up_tokenization_spaces`.
:type clean_up_tokenization_spaces: `bool`, *optional*
:param kwargs: Will be passed to the underlying model specific decode method.
:type kwargs: additional keyword arguments, *optional*
:Returns: **`str`** -- The decoded sentence.
.. py:method:: get_special_tokens_mask(token_ids_0, token_ids_1 = None, already_has_special_tokens = False)
Retrieves 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` or `encode_plus` methods.
:param token_ids_0: List of ids of the first sequence.
:type token_ids_0: `List[int]`
:param token_ids_1: List of ids of the second sequence.
:type token_ids_1: `List[int]`, *optional*
:param already_has_special_tokens: Whether or not the token list is already formatted with special tokens for the model.
:type already_has_special_tokens: `bool`, *optional*, defaults to `False`
:Returns: **A list of integers in the range [0, 1]** -- 1 for a special token, 0 for a sequence token.
.. py:method:: clean_up_tokenization(out_string)
:staticmethod:
Clean up a list of simple English tokenization artifacts like spaces before punctuations and abbreviated forms.
:param out_string: The text to clean up.
:type out_string: `str`
:Returns: **`str`** -- The cleaned-up string.
.. py:method:: _eventual_warn_about_too_long_sequence(ids, max_length, verbose)
Depending on the input and internal state we might trigger a warning about a sequence that is too long for its
corresponding model
:param ids: The ids produced by the tokenization
:type ids: `List[str]`
:param max_length: The max_length desired (does not trigger a warning if it is set)
:type max_length: `int`, *optional*
:param verbose: Whether or not to print more information and warnings.
:type verbose: `bool`
.. py:method:: _switch_to_input_mode()
Private method to put the tokenizer in input mode (when it has different modes for input/outputs)
.. py:method:: _switch_to_target_mode()
Private method to put the tokenizer in target mode (when it has different modes for input/outputs)
.. py:method:: as_target_tokenizer()
Temporarily sets the tokenizer for encoding the targets. Useful for tokenizer associated to
sequence-to-sequence models that need a slightly different processing for the labels.
.. py:method:: register_for_auto_class(auto_class='AutoTokenizer')
:classmethod:
Register this class with a given auto class. This should only be used for custom tokenizers as the ones in the
library are already mapped with `AutoTokenizer`.
This API is experimental and may have some slight breaking changes in the next releases.
:param auto_class: The auto class to register this new tokenizer with.
:type auto_class: `str` or `type`, *optional*, defaults to `"AutoTokenizer"`
.. py:method:: prepare_seq2seq_batch(src_texts, tgt_texts = None, max_length = None, max_target_length = None, padding = 'longest', return_tensors = None, truncation = True, **kwargs)
Prepare model inputs for translation. For best performance, translate one sentence at a time.
:param src_texts: List of documents to summarize or source language texts.
:type src_texts: `List[str]`
:param tgt_texts: List of summaries or target language texts.
:type tgt_texts: `list`, *optional*
:param max_length: Controls the maximum length for encoder inputs (documents to summarize or source language texts) If
left unset or set to `None`, this will use the predefined model maximum length if a maximum length is
required by one of the truncation/padding parameters. If the model has no specific maximum input length
(like XLNet) truncation/padding to a maximum length will be deactivated.
:type max_length: `int`, *optional*
:param max_target_length: Controls the maximum length of decoder inputs (target language texts or summaries) If left unset or set
to `None`, this will use the max_length value.
:type max_target_length: `int`, *optional*
:param padding: Activates and controls padding. Accepts the following values:
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
sequence if provided).
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
acceptable input length for the model if that argument is not provided.
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
lengths).
:type padding: `bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`
:param return_tensors: If set, will return tensors instead of list of python integers. Acceptable values are:
- `'tf'`: Return TensorFlow `tf.constant` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return Numpy `np.ndarray` objects.
:type return_tensors: `str` or [`~utils.TensorType`], *optional*
:param truncation: Activates and controls truncation. Accepts the following values:
- `True` or `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or
to the maximum acceptable input length for the model if that argument is not provided. This will
truncate token by token, removing a token from the longest sequence in the pair if a pair of
sequences (or a batch of pairs) is provided.
- `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
maximum acceptable input length for the model if that argument is not provided. This will only
truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
- `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the
maximum acceptable input length for the model if that argument is not provided. This will only
truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
- `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths
greater than the model maximum admissible input size).
:type truncation: `bool`, `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `True`
:param \*\*kwargs: Additional keyword arguments passed along to `self.__call__`.
:returns: A [`BatchEncoding`] with the following fields:
- **input_ids** -- List of token ids to be fed to the encoder.
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model.
- **labels** -- List of token ids for tgt_texts.
The full set of keys `[input_ids, attention_mask, labels]`, will only be returned if tgt_texts is passed.
Otherwise, input_ids, attention_mask will be the only keys.
:rtype: [`BatchEncoding`]
.. py:attribute:: SPECIAL_TOKENS_ATTRIBUTES
:value: ['bos_token', 'eos_token', 'unk_token', 'sep_token', 'pad_token', 'cls_token', 'mask_token',...
.. py:attribute:: _pad_token_type_id
:value: 0
.. py:attribute:: verbose
:value: False
.. py:attribute:: _special_tokens_map
.. py:method:: sanitize_special_tokens()
The `sanitize_special_tokens` is now deprecated kept for backward compatibility and will be removed in
transformers v5.
.. py:method:: add_special_tokens(special_tokens_dict, replace_additional_special_tokens=True)
Add a dictionary of special tokens (eos, pad, cls, etc.) to the encoder and link them to class attributes. If
special tokens are NOT in the vocabulary, they are added to it (indexed starting from the last index of the
current vocabulary).
When adding new tokens to the vocabulary, you should make sure to also resize the token embedding matrix of the
model so that its embedding matrix matches the tokenizer.
In order to do that, please use the [`~PreTrainedModel.resize_token_embeddings`] method.
Using `add_special_tokens` will ensure your special tokens can be used in several ways:
- Special tokens can be skipped when decoding using `skip_special_tokens = True`.
- Special tokens are carefully handled by the tokenizer (they are never split), similar to `AddedTokens`.
- You can easily refer to special tokens using tokenizer class attributes like `tokenizer.cls_token`. This
makes it easy to develop model-agnostic training and fine-tuning scripts.
When possible, special tokens are already registered for provided pretrained models (for instance
[`BertTokenizer`] `cls_token` is already registered to be :obj*'[CLS]'* and XLM's one is also registered to be
`''`).
:param special_tokens_dict: Keys should be in the list of predefined special attributes: [`bos_token`, `eos_token`, `unk_token`,
`sep_token`, `pad_token`, `cls_token`, `mask_token`, `additional_special_tokens`].
Tokens are only added if they are not already in the vocabulary (tested by checking if the tokenizer
assign the index of the `unk_token` to them).
:type special_tokens_dict: dictionary *str* to *str* or `tokenizers.AddedToken`
:param replace_additional_special_tokens: If `True`, the existing list of additional special tokens will be replaced by the list provided in
`special_tokens_dict`. Otherwise, `self._special_tokens_map["additional_special_tokens"]` is just extended. In the former
case, the tokens will NOT be removed from the tokenizer's full vocabulary - they are only being flagged
as non-special tokens. Remember, this only affects which tokens are skipped during decoding, not the
`added_tokens_encoder` and `added_tokens_decoder`. This means that the previous
`additional_special_tokens` are still added tokens, and will not be split by the model.
:type replace_additional_special_tokens: `bool`, *optional*,, defaults to `True`
:Returns: **`int`** -- Number of tokens added to the vocabulary.
Examples:
```python
# Let's see how to add a new classification token to GPT-2
tokenizer = GPT2Tokenizer.from_pretrained("openai-community/gpt2")
model = GPT2Model.from_pretrained("openai-community/gpt2")
special_tokens_dict = {"cls_token": ""}
num_added_toks = tokenizer.add_special_tokens(special_tokens_dict)
print("We have added", num_added_toks, "tokens")
# Notice: resize_token_embeddings expect to receive the full size of the new vocabulary, i.e., the length of the tokenizer.
model.resize_token_embeddings(len(tokenizer))
assert tokenizer.cls_token == ""
```
.. py:method:: add_tokens(new_tokens, special_tokens = False)
Add a list of new tokens to the tokenizer class. If the new tokens are not in the vocabulary, they are added to
it with indices starting from length of the current vocabulary and will be isolated before the tokenization
algorithm is applied. Added tokens and tokens from the vocabulary of the tokenization algorithm are therefore
not treated in the same way.
Note, when adding new tokens to the vocabulary, you should make sure to also resize the token embedding matrix
of the model so that its embedding matrix matches the tokenizer.
In order to do that, please use the [`~PreTrainedModel.resize_token_embeddings`] method.
:param new_tokens: Tokens are only added if they are not already in the vocabulary. `tokenizers.AddedToken` wraps a string
token to let you personalize its behavior: whether this token should only match against a single word,
whether this token should strip all potential whitespaces on the left side, whether this token should
strip all potential whitespaces on the right side, etc.
:type new_tokens: `str`, `tokenizers.AddedToken` or a list of *str* or `tokenizers.AddedToken`
:param special_tokens: Can be used to specify if the token is a special token. This mostly change the normalization behavior
(special tokens like CLS or [MASK] are usually not lower-cased for instance).
See details for `tokenizers.AddedToken` in HuggingFace tokenizers library.
:type special_tokens: `bool`, *optional*, defaults to `False`
:Returns: **`int`** -- Number of tokens added to the vocabulary.
Examples:
```python
# Let's see how to increase the vocabulary of Bert model and tokenizer
tokenizer = BertTokenizerFast.from_pretrained("google-bert/bert-base-uncased")
model = BertModel.from_pretrained("google-bert/bert-base-uncased")
num_added_toks = tokenizer.add_tokens(["new_tok1", "my_new-tok2"])
print("We have added", num_added_toks, "tokens")
# Notice: resize_token_embeddings expect to receive the full size of the new vocabulary, i.e., the length of the tokenizer.
model.resize_token_embeddings(len(tokenizer))
```
.. py:property:: pad_token_type_id
:type: int
Id of the padding token type in the vocabulary.
:type: `int`
.. py:method:: __setattr__(key, value)
.. py:method:: __getattr__(key)
.. py:property:: special_tokens_map
:type: Dict[str, Union[str, List[str]]]
A dictionary mapping special token class attributes (`cls_token`,
`unk_token`, etc.) to their values (`''`, `''`, etc.).
Convert potential tokens of `tokenizers.AddedToken` type to string.
:type: `Dict[str, Union[str, List[str]]]`
.. py:property:: special_tokens_map_extended
:type: Dict[str, Union[str, tokenizers.AddedToken, List[Union[str, tokenizers.AddedToken]]]]
A dictionary mapping
special token class attributes (`cls_token`, `unk_token`, etc.) to their values (`''`, `''`, etc.).
Don't convert tokens of `tokenizers.AddedToken` type to string so they can be used to control more finely how
special tokens are tokenized.
:type: `Dict[str, Union[str, tokenizers.AddedToken, List[Union[str, tokenizers.AddedToken]]]]`
.. py:property:: all_special_tokens_extended
:type: List[Union[str, tokenizers.AddedToken]]
All the special tokens (`''`, `''`, etc.), the order has
nothing to do with the index of each tokens. If you want to know the correct indices, check
`self.added_tokens_encoder`. We can't create an order anymore as the keys are `AddedTokens` and not `Strings`.
Don't convert tokens of `tokenizers.AddedToken` type to string so they can be used to control more finely how
special tokens are tokenized.
:type: `List[Union[str, tokenizers.AddedToken]]`
.. py:property:: all_special_tokens
:type: List[str]
A list of the unique special tokens (`''`, `''`, ..., etc.).
Convert tokens of `tokenizers.AddedToken` type to string.
:type: `List[str]`
.. py:property:: all_special_ids
:type: List[int]
List the ids of the special tokens(`''`, `''`, etc.) mapped to class attributes.
:type: `List[int]`
.. py:method:: _set_model_specific_special_tokens(special_tokens)
Adds new special tokens to the "SPECIAL_TOKENS_ATTRIBUTES" list which will be part
of "self.special_tokens" and saved as a special token in tokenizer's config.
This allows us to dynamically add new model-type specific tokens after initilizing the tokenizer.
For example: if the model tokenizers is multimodal, we can support special image or audio tokens.
.. py:method:: _create_repo(repo_id, private = None, token = None, repo_url = None, organization = None)
Create the repo if needed, cleans up repo_id with deprecated kwargs `repo_url` and `organization`, retrieves
the token.
.. py:method:: _get_files_timestamps(working_dir)
Returns the list of files with their last modification timestamp.
.. py:method:: _upload_modified_files(working_dir, repo_id, files_timestamps, commit_message = None, token = None, create_pr = False, revision = None, commit_description = None)
Uploads all modified files in `working_dir` to `repo_id`, based on `files_timestamps`.
.. py:method:: push_to_hub(repo_id, use_temp_dir = None, commit_message = None, private = None, token = None, max_shard_size = '5GB', create_pr = False, safe_serialization = True, revision = None, commit_description = None, tags = None, **deprecated_kwargs)
Upload the {object_files} to the 🤗 Model Hub.
:param repo_id: The name of the repository you want to push your {object} to. It should contain your organization name
when pushing to a given organization.
:type repo_id: `str`
:param use_temp_dir: Whether or not to use a temporary directory to store the files saved before they are pushed to the Hub.
Will default to `True` if there is no directory named like `repo_id`, `False` otherwise.
:type use_temp_dir: `bool`, *optional*
:param commit_message: Message to commit while pushing. Will default to `"Upload {object}"`.
:type commit_message: `str`, *optional*
:param private: Whether to make the repo private. If `None` (default), the repo will be public unless the organization's default is private. This value is ignored if the repo already exists.
:type private: `bool`, *optional*
:param token: The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
when running `huggingface-cli login` (stored in `~/.huggingface`). Will default to `True` if `repo_url`
is not specified.
:type token: `bool` or `str`, *optional*
:param max_shard_size: Only applicable for models. The maximum size for a checkpoint before being sharded. Checkpoints shard
will then be each of size lower than this size. If expressed as a string, needs to be digits followed
by a unit (like `"5MB"`). We default it to `"5GB"` so that users can easily load models on free-tier
Google Colab instances without any CPU OOM issues.
:type max_shard_size: `int` or `str`, *optional*, defaults to `"5GB"`
:param create_pr: Whether or not to create a PR with the uploaded files or directly commit.
:type create_pr: `bool`, *optional*, defaults to `False`
:param safe_serialization: Whether or not to convert the model weights in safetensors format for safer serialization.
:type safe_serialization: `bool`, *optional*, defaults to `True`
:param revision: Branch to push the uploaded files to.
:type revision: `str`, *optional*
:param commit_description: The description of the commit that will be created
:type commit_description: `str`, *optional*
:param tags: List of tags to push on the Hub.
:type tags: `List[str]`, *optional*
Examples:
```python
from transformers import {object_class}
{object} = {object_class}.from_pretrained("google-bert/bert-base-cased")
# Push the {object} to your namespace with the name "my-finetuned-bert".
{object}.push_to_hub("my-finetuned-bert")
# Push the {object} to an organization with the name "my-finetuned-bert".
{object}.push_to_hub("huggingface/my-finetuned-bert")
```
.. py:class:: ConfigRelCAT(/, **data)
Bases: :py:obj:`medcat.config.config.ComponentConfig`
The RelCAT part of the config
.. py:attribute:: general
:type: General
.. py:attribute:: model
:type: Model
.. py:attribute:: train
:type: Train
.. py:class:: Config
.. py:attribute:: extra
:value: 'allow'
.. py:attribute:: validate_assignment
:value: True
.. py:method:: load(load_path = './')
:classmethod:
Load the config from a file.
:param load_path: Path to RelCAT config. Defaults to "./".
:type load_path: str
:Returns: **ConfigRelCAT** -- The loaded config.
.. py:attribute:: comp_name
:type: str
:value: 'default'
The name of the component.
If a custom implementation is required, it needs to be registered
using `medcat.components.types.register_core_component(
, , )
By default, only the 'default' component is registered.
.. py:attribute:: _is_dirty
:type: bool
:value: False
.. py:method:: __setattr__(name, value)
.. py:property:: is_dirty
:type: bool
.. py:method:: mark_clean()
.. py:method:: get_strategy()
.. py:method:: get_init_attrs()
:classmethod:
.. py:method:: ignore_attrs()
:classmethod:
.. py:method:: include_properties()
:classmethod:
.. py:method:: merge_config(other)
Merge this config with another config's (partial) model dump.
The exepctation is that the `other` dict is a partial model dump.
Values specified there are overwritten into the current config.
Values not specified there are left intact.
The `other` config can have keys/values that do not exist in the
config or sub-config. And they will be added where possible.
:param other: The model dump
:type other: dict
:raises IncorrectConfigValues: If unable to set the attribute,
trying to set incorrect value, or trying to set sub-config
values in an incorrect format (non-dict).
.. py:attribute:: model_config
:type: ClassVar[pydantic.config.ConfigDict]
Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].
.. py:attribute:: model_fields
:type: ClassVar[Dict[str, pydantic.fields.FieldInfo]]
Metadata about the fields defined on the model,
mapping of field names to [`FieldInfo`][pydantic.fields.FieldInfo] objects.
This replaces `Model.__fields__` from Pydantic V1.
.. py:attribute:: model_computed_fields
:type: ClassVar[Dict[str, pydantic.fields.ComputedFieldInfo]]
A dictionary of computed field names and their corresponding `ComputedFieldInfo` objects.
.. py:attribute:: __class_vars__
:type: ClassVar[set[str]]
The names of the class variables defined on the model.
.. py:attribute:: __private_attributes__
:type: ClassVar[Dict[str, pydantic.fields.ModelPrivateAttr]]
Metadata about the private attributes of the model.
.. py:attribute:: __signature__
:type: ClassVar[inspect.Signature]
The synthesized `__init__` [`Signature`][inspect.Signature] of the model.
.. py:attribute:: __pydantic_complete__
:type: ClassVar[bool]
:value: False
Whether model building is completed, or if there are still undefined fields.
.. py:attribute:: __pydantic_core_schema__
:type: ClassVar[pydantic_core.CoreSchema]
The core schema of the model.
.. py:attribute:: __pydantic_custom_init__
:type: ClassVar[bool]
Whether the model has a custom `__init__` method.
.. py:attribute:: __pydantic_decorators__
:type: ClassVar[pydantic._internal._decorators.DecoratorInfos]
Metadata containing the decorators defined on the model.
This replaces `Model.__validators__` and `Model.__root_validators__` from Pydantic V1.
.. py:attribute:: __pydantic_generic_metadata__
:type: ClassVar[pydantic._internal._generics.PydanticGenericMetadata]
Metadata for generic models; contains data used for a similar purpose to
__args__, __origin__, __parameters__ in typing-module generics. May eventually be replaced by these.
.. py:attribute:: __pydantic_parent_namespace__
:type: ClassVar[Dict[str, Any] | None]
:value: None
Parent namespace of the model, used for automatic rebuilding of models.
.. py:attribute:: __pydantic_post_init__
:type: ClassVar[None | Literal['model_post_init']]
The name of the post-init method for the model, if defined.
.. py:attribute:: __pydantic_root_model__
:type: ClassVar[bool]
:value: False
Whether the model is a [`RootModel`][pydantic.root_model.RootModel].
.. py:attribute:: __pydantic_serializer__
:type: ClassVar[pydantic_core.SchemaSerializer]
The `pydantic-core` `SchemaSerializer` used to dump instances of the model.
.. py:attribute:: __pydantic_validator__
:type: ClassVar[pydantic_core.SchemaValidator | pydantic.plugin._schema_validator.PluggableSchemaValidator]
The `pydantic-core` `SchemaValidator` used to validate instances of the model.
.. py:attribute:: __pydantic_extra__
:type: dict[str, Any] | None
A dictionary containing extra values, if [`extra`][pydantic.config.ConfigDict.extra] is set to `'allow'`.
.. py:attribute:: __pydantic_fields_set__
:type: set[str]
The names of fields explicitly set during instantiation.
.. py:attribute:: __pydantic_private__
:type: dict[str, Any] | None
Values of private attributes set on the model instance.
.. py:attribute:: __slots__
:value: ('__dict__', '__pydantic_fields_set__', '__pydantic_extra__', '__pydantic_private__')
.. py:method:: __init__(/, **data)
Create a new model by parsing and validating input data from keyword arguments.
Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
validated to form a valid model.
`self` is explicitly positional-only to allow `self` as a field name.
.. py:property:: model_extra
:type: dict[str, Any] | None
Get extra fields set during validation.
:Returns: **A dictionary of extra fields, or `None` if `config.extra` is not set to `"allow"`.**
.. py:property:: model_fields_set
:type: set[str]
Returns the set of fields that have been explicitly set on this model instance.
:Returns: **A set of strings representing the fields that have been set,** -- i.e. that were not filled from defaults.
.. py:method:: model_construct(_fields_set = None, **values)
:classmethod:
Creates a new instance of the `Model` class with validated data.
Creates a new model setting `__dict__` and `__pydantic_fields_set__` from trusted or pre-validated data.
Default values are respected, but no other validation is performed.
!!! note
`model_construct()` generally respects the `model_config.extra` setting on the provided model.
That is, if `model_config.extra == 'allow'`, then all extra passed values are added to the model instance's `__dict__`
and `__pydantic_extra__` fields. If `model_config.extra == 'ignore'` (the default), then all extra passed values are ignored.
Because no validation is performed with a call to `model_construct()`, having `model_config.extra == 'forbid'` does not result in
an error if extra values are passed, but they will be ignored.
:param _fields_set: A set of field names that were originally explicitly set during instantiation. If provided,
this is directly used for the [`model_fields_set`][pydantic.BaseModel.model_fields_set] attribute.
Otherwise, the field names from the `values` argument will be used.
:param values: Trusted or pre-validated data dictionary.
:Returns: **A new instance of the `Model` class with validated data.**
.. py:method:: model_copy(*, update = None, deep = False)
Usage docs: https://docs.pydantic.dev/2.9/concepts/serialization/#model_copy
Returns a copy of the model.
:param update: Values to change/add in the new model. Note: the data is not validated
before creating the new model. You should trust this data.
:param deep: Set to `True` to make a deep copy of the model.
:Returns: **New model instance.**
.. py:method:: model_dump(*, mode = 'python', include = None, exclude = None, context = None, by_alias = False, exclude_unset = False, exclude_defaults = False, exclude_none = False, round_trip = False, warnings = True, serialize_as_any = False)
Usage docs: https://docs.pydantic.dev/2.9/concepts/serialization/#modelmodel_dump
Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
:param mode: The mode in which `to_python` should run.
If mode is 'json', the output will only contain JSON serializable types.
If mode is 'python', the output may contain non-JSON-serializable Python objects.
:param include: A set of fields to include in the output.
:param exclude: A set of fields to exclude from the output.
:param context: Additional context to pass to the serializer.
:param by_alias: Whether to use the field's alias in the dictionary key if defined.
:param exclude_unset: Whether to exclude fields that have not been explicitly set.
:param exclude_defaults: Whether to exclude fields that are set to their default value.
:param exclude_none: Whether to exclude fields that have a value of `None`.
:param round_trip: If True, dumped values should be valid as input for non-idempotent types such as Json[T].
:param warnings: How to handle serialization errors. False/"none" ignores them, True/"warn" logs errors,
"error" raises a [`PydanticSerializationError`][pydantic_core.PydanticSerializationError].
:param serialize_as_any: Whether to serialize fields with duck-typing serialization behavior.
:Returns: **A dictionary representation of the model.**
.. py:method:: model_dump_json(*, indent = None, include = None, exclude = None, context = None, by_alias = False, exclude_unset = False, exclude_defaults = False, exclude_none = False, round_trip = False, warnings = True, serialize_as_any = False)
Usage docs: https://docs.pydantic.dev/2.9/concepts/serialization/#modelmodel_dump_json
Generates a JSON representation of the model using Pydantic's `to_json` method.
:param indent: Indentation to use in the JSON output. If None is passed, the output will be compact.
:param include: Field(s) to include in the JSON output.
:param exclude: Field(s) to exclude from the JSON output.
:param context: Additional context to pass to the serializer.
:param by_alias: Whether to serialize using field aliases.
:param exclude_unset: Whether to exclude fields that have not been explicitly set.
:param exclude_defaults: Whether to exclude fields that are set to their default value.
:param exclude_none: Whether to exclude fields that have a value of `None`.
:param round_trip: If True, dumped values should be valid as input for non-idempotent types such as Json[T].
:param warnings: How to handle serialization errors. False/"none" ignores them, True/"warn" logs errors,
"error" raises a [`PydanticSerializationError`][pydantic_core.PydanticSerializationError].
:param serialize_as_any: Whether to serialize fields with duck-typing serialization behavior.
:Returns: **A JSON string representation of the model.**
.. py:method:: model_json_schema(by_alias = True, ref_template = DEFAULT_REF_TEMPLATE, schema_generator = GenerateJsonSchema, mode = 'validation')
:classmethod:
Generates a JSON schema for a model class.
:param by_alias: Whether to use attribute aliases or not.
:param ref_template: The reference template.
:param schema_generator: To override the logic used to generate the JSON schema, as a subclass of
`GenerateJsonSchema` with your desired modifications
:param mode: The mode in which to generate the schema.
:Returns: **The JSON schema for the given model class.**
.. py:method:: model_parametrized_name(params)
:classmethod:
Compute the class name for parametrizations of generic classes.
This method can be overridden to achieve a custom naming scheme for generic BaseModels.
:param params: Tuple of types of the class. Given a generic class
`Model` with 2 type variables and a concrete model `Model[str, int]`,
the value `(str, int)` would be passed to `params`.
:Returns: **String representing the new class where `params` are passed to `cls` as type variables.**
:raises TypeError: Raised when trying to generate concrete names for non-generic models.
.. py:method:: model_post_init(__context)
Override this method to perform additional initialization after `__init__` and `model_construct`.
This is useful if you want to do some validation that requires the entire model to be initialized.
.. py:method:: model_rebuild(*, force = False, raise_errors = True, _parent_namespace_depth = 2, _types_namespace = None)
:classmethod:
Try to rebuild the pydantic-core schema for the model.
This may be necessary when one of the annotations is a ForwardRef which could not be resolved during
the initial attempt to build the schema, and automatic rebuilding fails.
:param force: Whether to force the rebuilding of the model schema, defaults to `False`.
:param raise_errors: Whether to raise errors, defaults to `True`.
:param _parent_namespace_depth: The depth level of the parent namespace, defaults to 2.
:param _types_namespace: The types namespace, defaults to `None`.
:Returns: * **Returns `None` if the schema is already "complete" and rebuilding was not required.**
* **If rebuilding _was_ required, returns `True` if rebuilding was successful, otherwise `False`.**
.. py:method:: model_validate(obj, *, strict = None, from_attributes = None, context = None)
:classmethod:
Validate a pydantic model instance.
:param obj: The object to validate.
:param strict: Whether to enforce types strictly.
:param from_attributes: Whether to extract data from object attributes.
:param context: Additional context to pass to the validator.
:raises ValidationError: If the object could not be validated.
:Returns: **The validated model instance.**
.. py:method:: model_validate_json(json_data, *, strict = None, context = None)
:classmethod:
Usage docs: https://docs.pydantic.dev/2.9/concepts/json/#json-parsing
Validate the given JSON data against the Pydantic model.
:param json_data: The JSON data to validate.
:param strict: Whether to enforce types strictly.
:param context: Extra variables to pass to the validator.
:Returns: **The validated Pydantic model.**
:raises ValidationError: If `json_data` is not a JSON string or the object could not be validated.
.. py:method:: model_validate_strings(obj, *, strict = None, context = None)
:classmethod:
Validate the given object with string data against the Pydantic model.
:param obj: The object containing string data to validate.
:param strict: Whether to enforce types strictly.
:param context: Extra variables to pass to the validator.
:Returns: **The validated Pydantic model.**
.. py:method:: __get_pydantic_core_schema__(source, handler, /)
:classmethod:
Hook into generating the model's CoreSchema.
:param source: The class we are generating a schema for.
This will generally be the same as the `cls` argument if this is a classmethod.
:param handler: A callable that calls into Pydantic's internal CoreSchema generation logic.
:Returns: **A `pydantic-core` `CoreSchema`.**
.. py:method:: __get_pydantic_json_schema__(core_schema, handler, /)
:classmethod:
Hook into generating the model's JSON schema.
:param core_schema: A `pydantic-core` CoreSchema.
You can ignore this argument and call the handler with a new CoreSchema,
wrap this CoreSchema (`{'type': 'nullable', 'schema': current_schema}`),
or just call the handler with the original schema.
:param handler: Call into Pydantic's internal JSON schema generation.
This will raise a `pydantic.errors.PydanticInvalidForJsonSchema` if JSON schema
generation fails.
Since this gets called by `BaseModel.model_json_schema` you can override the
`schema_generator` argument to that function to change JSON schema generation globally
for a type.
:Returns: **A JSON schema, as a Python object.**
.. py:method:: __pydantic_init_subclass__(**kwargs)
:classmethod:
This is intended to behave just like `__init_subclass__`, but is called by `ModelMetaclass`
only after the class is actually fully initialized. In particular, attributes like `model_fields` will
be present when this is called.
This is necessary because `__init_subclass__` will always be called by `type.__new__`,
and it would require a prohibitively large refactor to the `ModelMetaclass` to ensure that
`type.__new__` was called in such a manner that the class would already be sufficiently initialized.
This will receive the same `kwargs` that would be passed to the standard `__init_subclass__`, namely,
any kwargs passed to the class definition that aren't used internally by pydantic.
:param \*\*kwargs: Any keyword arguments passed to the class definition that aren't used internally
by pydantic.
.. py:method:: __class_getitem__(typevar_values)
:classmethod:
.. py:method:: __copy__()
Returns a shallow copy of the model.
.. py:method:: __deepcopy__(memo = None)
Returns a deep copy of the model.
.. py:method:: __getattr__(item)
.. py:method:: _check_frozen(name, value)
.. py:method:: __getstate__()
.. py:method:: __setstate__(state)
.. py:method:: __eq__(other)
.. py:method:: __init_subclass__(**kwargs)
:classmethod:
This signature is included purely to help type-checkers check arguments to class declaration, which
provides a way to conveniently set model_config key/value pairs.
```py
from pydantic import BaseModel
class MyModel(BaseModel, extra='allow'): ...
```
However, this may be deceiving, since the _actual_ calls to `__init_subclass__` will not receive any
of the config arguments, and will only receive any keyword arguments passed during class initialization
that are _not_ expected keys in ConfigDict. (This is due to the way `ModelMetaclass.__new__` works.)
:param \*\*kwargs: Keyword arguments passed to the class definition, which set model_config
.. note::
You may want to override `__pydantic_init_subclass__` instead, which behaves similarly but is called
*after* the class is fully initialized.
.. py:method:: __iter__()
So `dict(model)` works.
.. py:method:: __repr__()
.. py:method:: __repr_args__()
.. py:attribute:: __repr_name__
.. py:attribute:: __repr_str__
.. py:attribute:: __pretty__
.. py:attribute:: __rich_repr__
.. py:method:: __str__()
.. py:property:: __fields__
:type: dict[str, pydantic.fields.FieldInfo]
.. py:property:: __fields_set__
:type: set[str]
.. py:method:: dict(*, include = None, exclude = None, by_alias = False, exclude_unset = False, exclude_defaults = False, exclude_none = False)
.. py:method:: json(*, include = None, exclude = None, by_alias = False, exclude_unset = False, exclude_defaults = False, exclude_none = False, encoder = PydanticUndefined, models_as_dict = PydanticUndefined, **dumps_kwargs)
.. py:method:: parse_obj(obj)
:classmethod:
.. py:method:: parse_raw(b, *, content_type = None, encoding = 'utf8', proto = None, allow_pickle = False)
:classmethod:
.. py:method:: parse_file(path, *, content_type = None, encoding = 'utf8', proto = None, allow_pickle = False)
:classmethod:
.. py:method:: from_orm(obj)
:classmethod:
.. py:method:: construct(_fields_set = None, **values)
:classmethod:
.. py:method:: copy(*, include = None, exclude = None, update = None, deep = False)
Returns a copy of the model.
!!! warning "Deprecated"
This method is now deprecated; use `model_copy` instead.
If you need `include` or `exclude`, use:
```py
data = self.model_dump(include=include, exclude=exclude, round_trip=True)
data = {**data, **(update or {})}
copied = self.model_validate(data)
```
:param include: Optional set or mapping specifying which fields to include in the copied model.
:param exclude: Optional set or mapping specifying which fields to exclude in the copied model.
:param update: Optional dictionary of field-value pairs to override field values in the copied model.
:param deep: If True, the values of fields that are Pydantic models will be deep-copied.
:Returns: **A copy of the model with included, excluded and updated fields as specified.**
.. py:method:: schema(by_alias = True, ref_template = DEFAULT_REF_TEMPLATE)
:classmethod:
.. py:method:: schema_json(*, by_alias = True, ref_template = DEFAULT_REF_TEMPLATE, **dumps_kwargs)
:classmethod:
.. py:method:: validate(value)
:classmethod:
.. py:method:: update_forward_refs(**localns)
:classmethod:
.. py:method:: _iter(*args, **kwargs)
.. py:method:: _copy_and_set_values(*args, **kwargs)
.. py:method:: _get_value(*args, **kwargs)
:classmethod:
.. py:method:: _calculate_keys(*args, **kwargs)
.. py:data:: logger
.. py:function:: split_list_train_test_by_class(data, sample_limit = -1, test_size = 0.2, shuffle = True)
:param data: "output_relations": relation_instances,
see create_base_relations_from_doc/csv for data columns
:type data: list
:param sample_limit: Limit the number of samples per class,
useful for dataset balancing . Defaults to -1.
:type sample_limit: int
:param test_size: Defaults to 0.2.
:type test_size: float
:param shuffle: Shuffle data randomly. Defaults to True.
:type shuffle: bool
:Returns: **tuple[list, list]** -- Train and test datasets
.. py:function:: load_bin_file(file_name, path='./')
.. py:function:: save_bin_file(file_name, data, path='./')
.. py:function:: save_state(model, optimizer, scheduler, epoch = 1, best_f1 = 0.0, path = './', model_name = 'BERT', task = 'train', is_checkpoint=False, final_export=False)
Used by RelCAT.save() and RelCAT.train()
Saves the RelCAT model state.
For checkpointing multiple files are created, best_f1, loss etc. score.
If you want to export the model after training set final_export=True
and leave is_checkpoint=False.
:param model: BertMode | LlamaModel etc.
:type model: BaseModel
:param optimizer: Defaults to None.
:type optimizer: torch.optim.AdamW, optional
:param scheduler: Defaults to None.
:type scheduler: torch.optim.lr_scheduler.MultiStepLR, optional
:param epoch: Defaults to None.
:type epoch: int
:param best_f1: Defaults to None.
:type best_f1: float
:param path: Defaults to "./".
:type path: str
:param model_name: . Defaults to "BERT". This is used to
checkpointing only.
:type model_name: str
:param task: Defaults to "train". This is used to checkpointing only.
:type task: str
:param is_checkpoint: Defaults to False.
:type is_checkpoint: bool
:param final_export: Defaults to False, if True then is_checkpoint
must be False also. Exports model.state_dict(),
out into "model.dat".
:type final_export: bool
.. py:function:: load_state(model, optimizer, scheduler, path = './', model_name = 'BERT', file_prefix = 'train', load_best = False, relcat_config = ConfigRelCAT())
Used by RelCAT.load() and RelCAT.train()
:param model: RelExtrBaseModel,
it has to be initialized before calling this method via
RelExtr(Bert/Llama)Model(...)
:type model: RelExtrBaseModel
:param optimizer: optimizer
:type optimizer: _type_
:param scheduler: scheduler
:type scheduler: _type_
:param path: Defaults to "./".
:type path: str, optional
:param model_name: Defaults to "BERT".
:type model_name: str, optional
:param file_prefix: Defaults to "train".
:type file_prefix: str, optional
:param load_best: Defaults to False.
:type load_best: bool, optional
:param relcat_config: Defaults to ConfigRelCAT().
:type relcat_config: ConfigRelCAT
:Returns: **tuple** (*int, int*) -- last epoch and f1 score.
.. py:function:: save_results(data, model_name = 'BERT', path = './', file_prefix = 'train')
.. py:function:: load_results(path, model_name = 'BERT', file_prefix = 'train')
.. py:function:: create_tokenizer_pretrain(tokenizer, relcat_config)
This method simply adds the default special tokens that we ecounter.
:param tokenizer: BERT/Llama tokenizer.
:type tokenizer: BaseTokenizerWrapper
:param relcat_config: The RelCAT config.
:type relcat_config: ConfigRelCAT
:Returns: **BaseTokenizerWrapper** -- The same tokenizer.
.. py:function:: create_dense_layers(relcat_config)
.. py:function:: get_annotation_schema_tag(sequence_output, input_ids, special_tag)
Gets to token sequences from the sequence_ouput for the specific token
tag ids in self.relcat_config.general.annotation_schema_tag_ids.
:param sequence_output: hidden states/embeddings for
each token in the input text
:type sequence_output: torch.Tensor
:param input_ids: input token ids
:type input_ids: torch.Tensor
:param special_tag: special annotation token id pairs
:type special_tag: list
:Returns: **torch.Tensor** -- new seq_tags