Transformers documentation

Splinter

Transformers

You are viewing v4.16.2 version. A newer version v4.46.3 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Splinter

Overview

The Splinter model was proposed in Few-Shot Question Answering by Pretraining Span Selection by Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson, Omer Levy. Splinter is an encoder-only transformer (similar to BERT) pretrained using the recurring span selection task on a large corpus comprising Wikipedia and the Toronto Book Corpus.

The abstract from the paper is the following:

In several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where only a few hundred training examples are available, and observe that standard models perform poorly, highlighting the discrepancy between current pretraining objectives and question answering. We propose a new pretraining scheme tailored for question answering: recurring span selection. Given a passage with multiple sets of recurring spans, we mask in each set all recurring spans but one, and ask the model to select the correct span in the passage for each masked span. Masked spans are replaced with a special token, viewed as a question representation, that is later used during fine-tuning to select the answer span. The resulting model obtains surprisingly good results on multiple benchmarks (e.g., 72.7 F1 on SQuAD with only 128 training examples), while maintaining competitive performance in the high-resource setting.

Tips:

Splinter was trained to predict answers spans conditioned on a special [QUESTION] token. These tokens contextualize to question representations which are used to predict the answers. This layer is called QASS, and is the default behaviour in the SplinterForQuestionAnswering class. Therefore:
Use SplinterTokenizer (rather than BertTokenizer), as it already contains this special token. Also, its default behavior is to use this token when two sequences are given (for example, in the run_qa.py script).
If you plan on using Splinter outside run_qa.py, please keep in mind the question token - it might be important for the success of your model, especially in a few-shot setting.
Please note there are two different checkpoints for each size of Splinter. Both are basically the same, except that one also has the pretrained wights of the QASS layer (tau/splinter-base-qass and tau/splinter-large-qass) and one doesn’t (tau/splinter-base and tau/splinter-large). This is done to support randomly initializing this layer at fine-tuning, as it is shown to yield better results for some cases in the paper.

This model was contributed by yuvalkirstain and oriram. The original code can be found here.

SplinterConfig

class transformers.SplinterConfig < source >

( 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 pad_token_id = 0 question_token_id = 104 **kwargs )

Parameters

vocab_size (int, optional, defaults to 30522) — Vocabulary size of the Splinter model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling SplinterModel.
hidden_size (int, optional, defaults to 768) — Dimension of the encoder layers and the pooler layer.
num_hidden_layers (int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder.
num_attention_heads (int, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (int, optional, defaults to 3072) — Dimension of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
hidden_act (str or function, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.
hidden_dropout_prob (float, optional, defaults to 0.1) — The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (float, optional, defaults to 0.1) — The dropout ratio for the attention probabilities.
max_position_embeddings (int, optional, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
type_vocab_size (int, optional, defaults to 2) — The vocabulary size of the token_type_ids passed when calling SplinterModel.
initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (float, optional, defaults to 1e-12) — The epsilon used by the layer normalization layers.
use_cache (bool, optional, defaults to 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.
question_token_id (int, optional, defaults to 104) — The id of the [QUESTION] token.

This is the configuration class to store the configuration of a SplinterModel. It is used to instantiate an Splinter 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 Splinter tau/splinter-base architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Example:

>>> from transformers import SplinterModel, SplinterConfig

>>> # Initializing a Splinter tau/splinter-base style configuration
>>> configuration = SplinterConfig()

>>> # Initializing a model from the tau/splinter-base style configuration
>>> model = SplinterModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

SplinterTokenizer

class transformers.SplinterTokenizer < source >

( vocab_file do_lower_case = True do_basic_tokenize = True never_split = None unk_token = '[UNK]' sep_token = '[SEP]' pad_token = '[PAD]' cls_token = '[CLS]' mask_token = '[MASK]' question_token = '[QUESTION]' tokenize_chinese_chars = True strip_accents = None **kwargs )

Parameters

vocab_file (str) — File containing the vocabulary.
do_lower_case (bool, optional, defaults to True) — Whether or not to lowercase the input when tokenizing.
do_basic_tokenize (bool, optional, defaults to True) — Whether or not to do basic tokenization before WordPiece.
never_split (Iterable, optional) — Collection of tokens which will never be split during tokenization. Only has an effect when do_basic_tokenize=True
unk_token (str, optional, defaults to "[UNK]") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
sep_token (str, optional, defaults to "[SEP]") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens.
pad_token (str, optional, defaults to "[PAD]") — The token used for padding, for example when batching sequences of different lengths.
cls_token (str, optional, defaults to "[CLS]") — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens.
mask_token (str, optional, defaults to "[MASK]") — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.
question_token (str, optional, defaults to "[QUESTION]") — The token used for constructing question representations.
tokenize_chinese_chars (bool, optional, defaults to True) — Whether or not to tokenize Chinese characters.

This should likely be deactivated for Japanese (see this issue). strip_accents — (bool, optional): Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for lowercase (as in the original BERT).

Construct a Splinter tokenizer. Based on WordPiece.

This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

build_inputs_with_special_tokens < source >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) → List[int]

Parameters

token_ids_0 (List[int]) — The question token IDs if pad_on_right, else context tokens IDs
token_ids_1 (List[int], optional) — The context token IDs if pad_on_right, else question token IDs

Returns

List[int]

List of input IDs with the appropriate special tokens.

Build model inputs from a pair of sequence for question answering tasks by concatenating and adding special tokens. A Splinter sequence has the following format:

single sequence: [CLS] X [SEP]
pair of sequences for question answering: [CLS] question_tokens [QUESTION] . [SEP] context_tokens [SEP]

get_special_tokens_mask < source >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None already_has_special_tokens: bool = False ) → List[int]

Parameters

token_ids_0 (List[int]) — List of IDs.
token_ids_1 (List[int], optional) — Optional second list of IDs for sequence pairs.
already_has_special_tokens (bool, optional, defaults to False) — Whether or not the token list is already formatted with special tokens for the model.

Returns

List[int]

A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer prepare_for_model method.

create_token_type_ids_from_sequences < source >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) → List[int]

Parameters

token_ids_0 (List[int]) — The first tokenized sequence.
token_ids_1 (List[int], optional) — The second tokenized sequence.

Returns

List[int]

The token type ids.

Create the token type IDs corresponding to the sequences passed. What are token type IDs?

Should be overridden in a subclass if the model has a special way of building those.

SplinterTokenizerFast

class transformers.SplinterTokenizerFast < source >

( vocab_file = None tokenizer_file = None do_lower_case = True unk_token = '[UNK]' sep_token = '[SEP]' pad_token = '[PAD]' cls_token = '[CLS]' mask_token = '[MASK]' question_token = '[QUESTION]' tokenize_chinese_chars = True strip_accents = None **kwargs )

Parameters

vocab_file (str) — File containing the vocabulary.
do_lower_case (bool, optional, defaults to True) — Whether or not to lowercase the input when tokenizing.
unk_token (str, optional, defaults to "[UNK]") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
sep_token (str, optional, defaults to "[SEP]") — The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens.
pad_token (str, optional, defaults to "[PAD]") — The token used for padding, for example when batching sequences of different lengths.
cls_token (str, optional, defaults to "[CLS]") — The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens.
mask_token (str, optional, defaults to "[MASK]") — The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict.
question_token (str, optional, defaults to "[QUESTION]") — The token used for constructing question representations.
clean_text (bool, optional, defaults to True) — Whether or not to clean the text before tokenization by removing any control characters and replacing all whitespaces by the classic one.
tokenize_chinese_chars (bool, optional, defaults to True) — Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see this issue). strip_accents — (bool, optional): Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for lowercase (as in the original BERT). wordpieces_prefix — (str, optional, defaults to "##"): The prefix for subwords.

Construct a “fast” Splinter tokenizer (backed by HuggingFace’s tokenizers library). Based on WordPiece.

This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

build_inputs_with_special_tokens < source >

( token_ids_0: typing.List[int] token_ids_1: typing.Optional[typing.List[int]] = None ) → List[int]

Parameters

token_ids_0 (List[int]) — The question token IDs if pad_on_right, else context tokens IDs
token_ids_1 (List[int], optional) — The context token IDs if pad_on_right, else question token IDs

Returns

List[int]

List of input IDs with the appropriate special tokens.

Build model inputs from a pair of sequence for question answering tasks by concatenating and adding special tokens. A Splinter sequence has the following format:

single sequence: [CLS] X [SEP]
pair of sequences for question answering: [CLS] question_tokens [QUESTION] . [SEP] context_tokens [SEP]

SplinterModel

class transformers.SplinterModel < source >

( config )

Parameters

config (SplinterConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

The bare Splinter Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

The model is an encoder (with only self-attention) following the architecture described in Attention is all you need by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.

forward < source >

( input_ids = None attention_mask = None token_type_ids = None position_ids = None head_mask = None inputs_embeds = None encoder_hidden_states = None encoder_attention_mask = None past_key_values = None use_cache = None output_attentions = None output_hidden_states = None return_dict = None ) → transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

Indices can be obtained using SplinterTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?
attention_mask (torch.FloatTensor of shape batch_size, sequence_length, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
token_type_ids (torch.LongTensor of shape batch_size, sequence_length, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
What are token type IDs?
position_ids (torch.LongTensor of shape batch_size, sequence_length, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

What are position IDs?
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
encoder_hidden_states (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.
encoder_attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
past_key_values (tuple(tuple(torch.FloatTensor)) of length config.n_layers with each tuple having 4 tensors of shape (batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).
use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

Returns

transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or tuple(torch.FloatTensor)

A transformers.modeling_outputs.BaseModelOutputWithPastAndCrossAttentions or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (SplinterConfig) and inputs.

last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.

If past_key_values is used only the last hidden-state of the sequences of shape (batch_size, 1, hidden_size) is output.
past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally if config.is_encoder_decoder=True 2 additional tensors of shape (batch_size, num_heads, encoder_sequence_length, embed_size_per_head).

Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if config.is_encoder_decoder=True in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.
hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
cross_attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True and config.add_cross_attention=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.

The SplinterModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

>>> from transformers import SplinterTokenizer, SplinterModel
>>> import torch

>>> tokenizer = SplinterTokenizer.from_pretrained("tau/splinter-base")
>>> model = SplinterModel.from_pretrained("tau/splinter-base")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state

SplinterForQuestionAnswering

class transformers.SplinterForQuestionAnswering < source >

( config )

Parameters

config (SplinterConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Splinter Model with a span classification head on top for extractive question-answering tasks like SQuAD (a linear layers on top of the hidden-states output to compute span start logits and span end logits).

This model is a PyTorch torch.nn.Module sub-class. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward < source >

( input_ids = None attention_mask = None token_type_ids = None position_ids = None head_mask = None inputs_embeds = None start_positions = None end_positions = None output_attentions = None output_hidden_states = None return_dict = None question_positions = None ) → transformers.modeling_outputs.QuestionAnsweringModelOutput or tuple(torch.FloatTensor)

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary.

Indices can be obtained using SplinterTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

What are input IDs?
attention_mask (torch.FloatTensor of shape batch_size, sequence_length, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
token_type_ids (torch.LongTensor of shape batch_size, sequence_length, optional) — Segment token indices to indicate first and second portions of the inputs. Indices are selected in [0, 1]:
- 0 corresponds to a sentence A token,
- 1 corresponds to a sentence B token.
What are token type IDs?
position_ids (torch.LongTensor of shape batch_size, sequence_length, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.max_position_embeddings - 1].

What are position IDs?
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model’s internal embedding lookup matrix.
output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
start_positions (torch.LongTensor of shape (batch_size,), optional) — Labels for position (index) of the start of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
end_positions (torch.LongTensor of shape (batch_size,), optional) — Labels for position (index) of the end of the labelled span for computing the token classification loss. Positions are clamped to the length of the sequence (sequence_length). Position outside of the sequence are not taken into account for computing the loss.
question_positions (torch.LongTensor of shape (batch_size, num_questions), optional) — The positions of all question tokens. If given, start_logits and end_logits will be of shape (batch_size, num_questions, sequence_length). If None, the first question token in each sequence in the batch will be the only one for which start_logits and end_logits are calculated and they will be of shape (batch_size, sequence_length).

Returns

transformers.modeling_outputs.QuestionAnsweringModelOutput or tuple(torch.FloatTensor)

A transformers.modeling_outputs.QuestionAnsweringModelOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (SplinterConfig) and inputs.

loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Total span extraction loss is the sum of a Cross-Entropy for the start and end positions.
start_logits (torch.FloatTensor of shape (batch_size, sequence_length)) — Span-start scores (before SoftMax).
end_logits (torch.FloatTensor of shape (batch_size, sequence_length)) — Span-end scores (before SoftMax).
hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The SplinterForQuestionAnswering forward method, overrides the __call__ special method.

Example:

>>> from transformers import SplinterTokenizer, SplinterForQuestionAnswering
>>> import torch

>>> tokenizer = SplinterTokenizer.from_pretrained("tau/splinter-base")
>>> model = SplinterForQuestionAnswering.from_pretrained("tau/splinter-base")

>>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
>>> inputs = tokenizer(question, text, return_tensors="pt")
>>> start_positions = torch.tensor([1])
>>> end_positions = torch.tensor([3])

>>> outputs = model(**inputs, start_positions=start_positions, end_positions=end_positions)
>>> loss = outputs.loss
>>> start_scores = outputs.start_logits
>>> end_scores = outputs.end_logits

←Speech2Text2 SqueezeBERT→