|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
"""PyTorch BERT model.""" |
|
|
|
|
|
import math |
|
import os |
|
import warnings |
|
from dataclasses import dataclass |
|
from typing import List, Optional, Tuple, Union |
|
import numpy as np |
|
|
|
import torch |
|
import torch.utils.checkpoint |
|
from torch import nn |
|
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss |
|
|
|
from transformers.activations import ACT2FN |
|
from transformers.modeling_outputs import ( |
|
BaseModelOutputWithPastAndCrossAttentions, |
|
BaseModelOutputWithPoolingAndCrossAttentions, |
|
CausalLMOutputWithCrossAttentions, |
|
MaskedLMOutput, |
|
MultipleChoiceModelOutput, |
|
NextSentencePredictorOutput, |
|
QuestionAnsweringModelOutput, |
|
SequenceClassifierOutput, |
|
TokenClassifierOutput, |
|
) |
|
from transformers.modeling_utils import PreTrainedModel |
|
from transformers.pytorch_utils import ( |
|
apply_chunking_to_forward, |
|
find_pruneable_heads_and_indices, |
|
prune_linear_layer, |
|
) |
|
from transformers.utils import ( |
|
ModelOutput, |
|
add_code_sample_docstrings, |
|
add_start_docstrings, |
|
add_start_docstrings_to_model_forward, |
|
logging, |
|
replace_return_docstrings, |
|
) |
|
from .configuration_bert import JinaBertConfig |
|
|
|
|
|
try: |
|
from torch.nn.functional import scaled_dot_product_attention |
|
except ImportError: |
|
scaled_dot_product_attention = None |
|
|
|
|
|
try: |
|
from tqdm.autonotebook import trange |
|
|
|
has_tqdm = True |
|
except ImportError: |
|
has_tqdm = False |
|
|
|
logger = logging.get_logger(__name__) |
|
|
|
_CHECKPOINT_FOR_DOC = "bert-base-uncased" |
|
_CONFIG_FOR_DOC = "JinaBertConfig" |
|
|
|
|
|
_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = ( |
|
"dbmdz/bert-large-cased-finetuned-conll03-english" |
|
) |
|
_TOKEN_CLASS_EXPECTED_OUTPUT = "['O', 'I-ORG', 'I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'I-LOC', 'O', 'I-LOC', 'I-LOC'] " |
|
_TOKEN_CLASS_EXPECTED_LOSS = 0.01 |
|
|
|
|
|
_CHECKPOINT_FOR_QA = "deepset/bert-base-cased-squad2" |
|
_QA_EXPECTED_OUTPUT = "'a nice puppet'" |
|
_QA_EXPECTED_LOSS = 7.41 |
|
_QA_TARGET_START_INDEX = 14 |
|
_QA_TARGET_END_INDEX = 15 |
|
|
|
|
|
_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "textattack/bert-base-uncased-yelp-polarity" |
|
_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'" |
|
_SEQ_CLASS_EXPECTED_LOSS = 0.01 |
|
|
|
|
|
def load_tf_weights_in_bert(model, config, tf_checkpoint_path): |
|
"""Load tf checkpoints in a pytorch model.""" |
|
try: |
|
import re |
|
|
|
import numpy as np |
|
import tensorflow as tf |
|
except ImportError: |
|
logger.error( |
|
"Loading a TensorFlow model in PyTorch, requires TensorFlow to be installed. Please see " |
|
"https://www.tensorflow.org/install/ for installation instructions." |
|
) |
|
raise |
|
tf_path = os.path.abspath(tf_checkpoint_path) |
|
logger.info(f"Converting TensorFlow checkpoint from {tf_path}") |
|
|
|
init_vars = tf.train.list_variables(tf_path) |
|
names = [] |
|
arrays = [] |
|
for name, shape in init_vars: |
|
logger.info(f"Loading TF weight {name} with shape {shape}") |
|
array = tf.train.load_variable(tf_path, name) |
|
names.append(name) |
|
arrays.append(array) |
|
|
|
for name, array in zip(names, arrays): |
|
name = name.split("/") |
|
|
|
|
|
if any( |
|
n |
|
in [ |
|
"adam_v", |
|
"adam_m", |
|
"AdamWeightDecayOptimizer", |
|
"AdamWeightDecayOptimizer_1", |
|
"global_step", |
|
] |
|
for n in name |
|
): |
|
logger.info(f"Skipping {'/'.join(name)}") |
|
continue |
|
pointer = model |
|
for m_name in name: |
|
if re.fullmatch(r"[A-Za-z]+_\d+", m_name): |
|
scope_names = re.split(r"_(\d+)", m_name) |
|
else: |
|
scope_names = [m_name] |
|
if scope_names[0] == "kernel" or scope_names[0] == "gamma": |
|
pointer = getattr(pointer, "weight") |
|
elif scope_names[0] == "output_bias" or scope_names[0] == "beta": |
|
pointer = getattr(pointer, "bias") |
|
elif scope_names[0] == "output_weights": |
|
pointer = getattr(pointer, "weight") |
|
elif scope_names[0] == "squad": |
|
pointer = getattr(pointer, "classifier") |
|
else: |
|
try: |
|
pointer = getattr(pointer, scope_names[0]) |
|
except AttributeError: |
|
logger.info(f"Skipping {'/'.join(name)}") |
|
continue |
|
if len(scope_names) >= 2: |
|
num = int(scope_names[1]) |
|
pointer = pointer[num] |
|
if m_name[-11:] == "_embeddings": |
|
pointer = getattr(pointer, "weight") |
|
elif m_name == "kernel": |
|
array = np.transpose(array) |
|
try: |
|
if pointer.shape != array.shape: |
|
raise ValueError( |
|
f"Pointer shape {pointer.shape} and array shape {array.shape} mismatched" |
|
) |
|
except ValueError as e: |
|
e.args += (pointer.shape, array.shape) |
|
raise |
|
logger.info(f"Initialize PyTorch weight {name}") |
|
pointer.data = torch.from_numpy(array) |
|
return model |
|
|
|
|
|
class JinaBertEmbeddings(nn.Module): |
|
"""Construct the embeddings from word, position and token_type embeddings.""" |
|
|
|
def __init__(self, config: JinaBertConfig): |
|
super().__init__() |
|
self.word_embeddings = nn.Embedding( |
|
config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id |
|
) |
|
if config.position_embedding_type != "alibi": |
|
self.position_embeddings = nn.Embedding( |
|
config.max_position_embeddings, config.hidden_size |
|
) |
|
self.token_type_embeddings = nn.Embedding( |
|
config.type_vocab_size, config.hidden_size |
|
) |
|
|
|
|
|
|
|
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
self.dropout = nn.Dropout(config.hidden_dropout_prob) |
|
|
|
self.position_embedding_type = getattr( |
|
config, "position_embedding_type", "absolute" |
|
) |
|
self.register_buffer( |
|
"position_ids", |
|
torch.arange(config.max_position_embeddings).expand((1, -1)), |
|
persistent=False, |
|
) |
|
self.register_buffer( |
|
"token_type_ids", |
|
torch.zeros(self.position_ids.size(), dtype=torch.long), |
|
persistent=False, |
|
) |
|
|
|
def forward( |
|
self, |
|
input_ids: Optional[torch.LongTensor] = None, |
|
token_type_ids: Optional[torch.LongTensor] = None, |
|
position_ids: Optional[torch.LongTensor] = None, |
|
inputs_embeds: Optional[torch.FloatTensor] = None, |
|
past_key_values_length: int = 0, |
|
) -> torch.Tensor: |
|
if input_ids is not None: |
|
input_shape = input_ids.size() |
|
else: |
|
input_shape = inputs_embeds.size()[:-1] |
|
|
|
seq_length = input_shape[1] |
|
|
|
if position_ids is None: |
|
position_ids = self.position_ids[ |
|
:, past_key_values_length : seq_length + past_key_values_length |
|
] |
|
|
|
|
|
|
|
|
|
if token_type_ids is None: |
|
if hasattr(self, "token_type_ids"): |
|
buffered_token_type_ids = self.token_type_ids[:, :seq_length] |
|
buffered_token_type_ids_expanded = buffered_token_type_ids.expand( |
|
input_shape[0], seq_length |
|
) |
|
token_type_ids = buffered_token_type_ids_expanded |
|
else: |
|
token_type_ids = torch.zeros( |
|
input_shape, dtype=torch.long, device=self.position_ids.device |
|
) |
|
|
|
if inputs_embeds is None: |
|
inputs_embeds = self.word_embeddings(input_ids) |
|
token_type_embeddings = self.token_type_embeddings(token_type_ids) |
|
|
|
embeddings = inputs_embeds + token_type_embeddings |
|
if self.position_embedding_type == "absolute": |
|
position_embeddings = self.position_embeddings(position_ids) |
|
embeddings += position_embeddings |
|
embeddings = self.LayerNorm(embeddings) |
|
embeddings = self.dropout(embeddings) |
|
return embeddings |
|
|
|
|
|
class JinaBertSelfAttention(nn.Module): |
|
def __init__(self, config: JinaBertConfig, position_embedding_type=None): |
|
super().__init__() |
|
if config.hidden_size % config.num_attention_heads != 0 and not hasattr( |
|
config, "embedding_size" |
|
): |
|
raise ValueError( |
|
f"The hidden size ({config.hidden_size}) is not a multiple of the number of attention " |
|
f"heads ({config.num_attention_heads})" |
|
) |
|
|
|
self.attn_implementation = config.attn_implementation |
|
self.num_attention_heads = config.num_attention_heads |
|
self.attention_head_size = int(config.hidden_size / config.num_attention_heads) |
|
self.all_head_size = self.num_attention_heads * self.attention_head_size |
|
|
|
self.query = nn.Linear(config.hidden_size, self.all_head_size) |
|
self.key = nn.Linear(config.hidden_size, self.all_head_size) |
|
self.value = nn.Linear(config.hidden_size, self.all_head_size) |
|
self.layer_norm_q = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
self.layer_norm_k = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
|
|
self.dropout = nn.Dropout(config.attention_probs_dropout_prob) |
|
self.position_embedding_type = position_embedding_type or getattr( |
|
config, "position_embedding_type", "absolute" |
|
) |
|
if ( |
|
self.position_embedding_type == "relative_key" |
|
or self.position_embedding_type == "relative_key_query" |
|
): |
|
self.max_position_embeddings = config.max_position_embeddings |
|
self.distance_embedding = nn.Embedding( |
|
2 * config.max_position_embeddings - 1, self.attention_head_size |
|
) |
|
|
|
self.is_decoder = config.is_decoder |
|
|
|
def transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor: |
|
new_x_shape = x.size()[:-1] + ( |
|
self.num_attention_heads, |
|
self.attention_head_size, |
|
) |
|
x = x.view(new_x_shape) |
|
return x.permute(0, 2, 1, 3) |
|
|
|
def forward( |
|
self, |
|
hidden_states: torch.Tensor, |
|
attention_mask: Optional[torch.FloatTensor] = None, |
|
head_mask: Optional[torch.FloatTensor] = None, |
|
encoder_hidden_states: Optional[torch.FloatTensor] = None, |
|
encoder_attention_mask: Optional[torch.FloatTensor] = None, |
|
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, |
|
output_attentions: Optional[bool] = False, |
|
bias: Optional[torch.FloatTensor] = None, |
|
) -> Tuple[torch.Tensor]: |
|
mixed_query_layer = self.layer_norm_q(self.query(hidden_states)) |
|
|
|
|
|
|
|
|
|
is_cross_attention = encoder_hidden_states is not None |
|
|
|
if is_cross_attention and past_key_value is not None: |
|
|
|
key_layer = past_key_value[0] |
|
value_layer = past_key_value[1] |
|
attention_mask = encoder_attention_mask |
|
elif is_cross_attention: |
|
key_layer = self.transpose_for_scores(self.layer_norm_k(self.key(encoder_hidden_states))) |
|
value_layer = self.transpose_for_scores(self.value(encoder_hidden_states)) |
|
attention_mask = encoder_attention_mask |
|
elif past_key_value is not None: |
|
key_layer = self.transpose_for_scores(self.layer_norm_k(self.key(hidden_states))) |
|
value_layer = self.transpose_for_scores(self.value(hidden_states)) |
|
key_layer = torch.cat([past_key_value[0], key_layer], dim=2) |
|
value_layer = torch.cat([past_key_value[1], value_layer], dim=2) |
|
else: |
|
key_layer = self.transpose_for_scores(self.layer_norm_k(self.key(hidden_states))) |
|
value_layer = self.transpose_for_scores(self.value(hidden_states)) |
|
|
|
query_layer = self.transpose_for_scores(mixed_query_layer) |
|
|
|
use_cache = past_key_value is not None |
|
if self.is_decoder: |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
past_key_value = (key_layer, value_layer) |
|
|
|
if self.attn_implementation == 'torch' and scaled_dot_product_attention is not None: |
|
b, _, s, _ = query_layer.shape |
|
new_bias = attention_mask + bias |
|
attn = scaled_dot_product_attention(query_layer, key_layer, value_layer, new_bias) |
|
attn = attn.permute(0, 2, 1, 3).contiguous() |
|
return (attn.view(b, s, self.all_head_size),) |
|
|
|
|
|
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2)) |
|
|
|
if ( |
|
self.position_embedding_type == "relative_key" |
|
or self.position_embedding_type == "relative_key_query" |
|
): |
|
query_length, key_length = query_layer.shape[2], key_layer.shape[2] |
|
if use_cache: |
|
position_ids_l = torch.tensor( |
|
key_length - 1, dtype=torch.long, device=hidden_states.device |
|
).view(-1, 1) |
|
else: |
|
position_ids_l = torch.arange( |
|
query_length, dtype=torch.long, device=hidden_states.device |
|
).view(-1, 1) |
|
position_ids_r = torch.arange( |
|
key_length, dtype=torch.long, device=hidden_states.device |
|
).view(1, -1) |
|
distance = position_ids_l - position_ids_r |
|
|
|
positional_embedding = self.distance_embedding( |
|
distance + self.max_position_embeddings - 1 |
|
) |
|
positional_embedding = positional_embedding.to( |
|
dtype=query_layer.dtype |
|
) |
|
|
|
if self.position_embedding_type == "relative_key": |
|
relative_position_scores = torch.einsum( |
|
"bhld,lrd->bhlr", query_layer, positional_embedding |
|
) |
|
attention_scores = attention_scores + relative_position_scores |
|
elif self.position_embedding_type == "relative_key_query": |
|
relative_position_scores_query = torch.einsum( |
|
"bhld,lrd->bhlr", query_layer, positional_embedding |
|
) |
|
relative_position_scores_key = torch.einsum( |
|
"bhrd,lrd->bhlr", key_layer, positional_embedding |
|
) |
|
attention_scores = ( |
|
attention_scores |
|
+ relative_position_scores_query |
|
+ relative_position_scores_key |
|
) |
|
|
|
attention_scores = attention_scores / math.sqrt(self.attention_head_size) |
|
if attention_mask is not None: |
|
|
|
attention_scores = attention_scores + attention_mask |
|
|
|
|
|
attention_probs = nn.functional.softmax(attention_scores + bias, dim=-1) |
|
|
|
|
|
|
|
attention_probs = self.dropout(attention_probs) |
|
|
|
|
|
if head_mask is not None: |
|
attention_probs = attention_probs * head_mask |
|
|
|
context_layer = torch.matmul(attention_probs, value_layer) |
|
|
|
context_layer = context_layer.permute(0, 2, 1, 3).contiguous() |
|
new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,) |
|
context_layer = context_layer.view(new_context_layer_shape) |
|
|
|
outputs = ( |
|
(context_layer, attention_probs) if output_attentions else (context_layer,) |
|
) |
|
|
|
if self.is_decoder: |
|
outputs = outputs + (past_key_value,) |
|
return outputs |
|
|
|
|
|
class JinaBertSelfOutput(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.dense = nn.Linear(config.hidden_size, config.hidden_size) |
|
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
self.dropout = nn.Dropout(config.hidden_dropout_prob) |
|
|
|
def forward( |
|
self, hidden_states: torch.Tensor, input_tensor: torch.Tensor |
|
) -> torch.Tensor: |
|
hidden_states = self.dense(hidden_states) |
|
hidden_states = self.dropout(hidden_states) |
|
hidden_states = self.LayerNorm(hidden_states + input_tensor) |
|
return hidden_states |
|
|
|
|
|
class JinaBertAttention(nn.Module): |
|
def __init__(self, config, position_embedding_type=None): |
|
super().__init__() |
|
self.self = JinaBertSelfAttention( |
|
config, position_embedding_type=position_embedding_type |
|
) |
|
self.output = JinaBertSelfOutput(config) |
|
self.pruned_heads = set() |
|
|
|
def prune_heads(self, heads): |
|
if len(heads) == 0: |
|
return |
|
heads, index = find_pruneable_heads_and_indices( |
|
heads, |
|
self.self.num_attention_heads, |
|
self.self.attention_head_size, |
|
self.pruned_heads, |
|
) |
|
|
|
|
|
self.self.query = prune_linear_layer(self.self.query, index) |
|
self.self.key = prune_linear_layer(self.self.key, index) |
|
self.self.value = prune_linear_layer(self.self.value, index) |
|
self.output.dense = prune_linear_layer(self.output.dense, index, dim=1) |
|
|
|
|
|
self.self.num_attention_heads = self.self.num_attention_heads - len(heads) |
|
self.self.all_head_size = ( |
|
self.self.attention_head_size * self.self.num_attention_heads |
|
) |
|
self.pruned_heads = self.pruned_heads.union(heads) |
|
|
|
def forward( |
|
self, |
|
hidden_states: torch.Tensor, |
|
attention_mask: Optional[torch.FloatTensor] = None, |
|
head_mask: Optional[torch.FloatTensor] = None, |
|
encoder_hidden_states: Optional[torch.FloatTensor] = None, |
|
encoder_attention_mask: Optional[torch.FloatTensor] = None, |
|
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, |
|
output_attentions: Optional[bool] = False, |
|
bias: Optional[torch.FloatTensor] = None, |
|
) -> Tuple[torch.Tensor]: |
|
self_outputs = self.self( |
|
hidden_states, |
|
attention_mask, |
|
head_mask, |
|
encoder_hidden_states, |
|
encoder_attention_mask, |
|
past_key_value, |
|
output_attentions, |
|
bias, |
|
) |
|
attention_output = self.output(self_outputs[0], hidden_states) |
|
outputs = (attention_output,) + self_outputs[ |
|
1: |
|
] |
|
return outputs |
|
|
|
|
|
class JinaBertMLP(nn.Module): |
|
def __init__(self, config: JinaBertConfig): |
|
super().__init__() |
|
self.config = config |
|
self.act = ACT2FN[config.hidden_act] |
|
self.up_layer = nn.Linear( |
|
config.hidden_size, config.intermediate_size, bias=False |
|
) |
|
self.down_layer = nn.Linear(config.intermediate_size, config.hidden_size) |
|
self.dropout = nn.Dropout(config.hidden_dropout_prob) |
|
|
|
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: |
|
|
|
hidden_mlp_states = self.act(self.up_layer(hidden_states)) |
|
hidden_mlp_states = self.dropout(hidden_mlp_states) |
|
|
|
return self.down_layer(hidden_mlp_states) |
|
|
|
|
|
class JinaBertGLUMLP(nn.Module): |
|
def __init__(self, config: JinaBertConfig): |
|
super().__init__() |
|
self.config = config |
|
if config.feed_forward_type == 'reglu': |
|
self.act = nn.ReLU() |
|
elif config.feed_forward_type == 'geglu': |
|
self.act = nn.GELU() |
|
else: |
|
raise ValueError( |
|
f"feed_forward_type {config.feed_forward_type} not supported" |
|
) |
|
self.up_gated_layer = nn.Linear( |
|
config.hidden_size, config.intermediate_size * 2, bias=False |
|
) |
|
self.down_layer = nn.Linear(config.intermediate_size, config.hidden_size) |
|
self.dropout = nn.Dropout(config.hidden_dropout_prob) |
|
|
|
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: |
|
|
|
hidden_mlp_states = self.up_gated_layer(hidden_states) |
|
up = hidden_mlp_states[:, :, :self.config.intermediate_size] |
|
gated = hidden_mlp_states[:, :, self.config.intermediate_size:] |
|
hidden_mlp_states = up * self.act(gated) |
|
hidden_mlp_states = self.dropout(hidden_mlp_states) |
|
|
|
return self.down_layer(hidden_mlp_states) |
|
|
|
|
|
class JinaBertLayer(nn.Module): |
|
def __init__(self, config: JinaBertConfig): |
|
super().__init__() |
|
self.chunk_size_feed_forward = config.chunk_size_feed_forward |
|
self.seq_len_dim = 1 |
|
self.attention = JinaBertAttention(config) |
|
self.is_decoder = config.is_decoder |
|
self.add_cross_attention = config.add_cross_attention |
|
self.feed_forward_type = config.feed_forward_type |
|
self.layer_norm_1 = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
self.layer_norm_2 = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
if self.add_cross_attention: |
|
if not self.is_decoder: |
|
raise ValueError( |
|
f"{self} should be used as a decoder model if cross attention is added" |
|
) |
|
self.crossattention = JinaBertAttention( |
|
config, position_embedding_type="absolute" |
|
) |
|
if self.feed_forward_type.endswith('glu'): |
|
self.mlp = JinaBertGLUMLP(config) |
|
else: |
|
self.mlp = JinaBertMLP(config) |
|
|
|
def forward( |
|
self, |
|
hidden_states: torch.Tensor, |
|
attention_mask: Optional[torch.FloatTensor] = None, |
|
head_mask: Optional[torch.FloatTensor] = None, |
|
encoder_hidden_states: Optional[torch.FloatTensor] = None, |
|
encoder_attention_mask: Optional[torch.FloatTensor] = None, |
|
bias: Optional[torch.FloatTensor] = None, |
|
past_key_value: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, |
|
output_attentions: Optional[bool] = False, |
|
) -> Tuple[torch.Tensor]: |
|
|
|
residual = hidden_states |
|
|
|
|
|
self_attn_past_key_value = ( |
|
past_key_value[:2] if past_key_value is not None else None |
|
) |
|
self_attention_outputs = self.attention( |
|
hidden_states, |
|
attention_mask, |
|
head_mask, |
|
output_attentions=output_attentions, |
|
past_key_value=self_attn_past_key_value, |
|
bias=bias, |
|
) |
|
attention_output = self_attention_outputs[0] |
|
|
|
|
|
if self.is_decoder: |
|
outputs = self_attention_outputs[1:-1] |
|
present_key_value = self_attention_outputs[-1] |
|
else: |
|
outputs = self_attention_outputs[ |
|
1: |
|
] |
|
|
|
cross_attn_present_key_value = None |
|
if self.is_decoder and encoder_hidden_states is not None: |
|
if not hasattr(self, "crossattention"): |
|
raise ValueError( |
|
f"If `encoder_hidden_states` are passed, {self} has to be instantiated with cross-attention layers" |
|
" by setting `config.add_cross_attention=True`" |
|
) |
|
|
|
|
|
cross_attn_past_key_value = ( |
|
past_key_value[-2:] if past_key_value is not None else None |
|
) |
|
cross_attention_outputs = self.crossattention( |
|
attention_output, |
|
attention_mask, |
|
head_mask, |
|
encoder_hidden_states, |
|
encoder_attention_mask, |
|
cross_attn_past_key_value, |
|
output_attentions, |
|
) |
|
attention_output = cross_attention_outputs[0] |
|
outputs = ( |
|
outputs + cross_attention_outputs[1:-1] |
|
) |
|
|
|
|
|
cross_attn_present_key_value = cross_attention_outputs[-1] |
|
present_key_value = present_key_value + cross_attn_present_key_value |
|
|
|
residual = self.layer_norm_1(residual + attention_output) |
|
mlp_output = self.mlp(residual) |
|
layer_output = self.layer_norm_2(residual + mlp_output) |
|
outputs = (layer_output,) + outputs |
|
|
|
|
|
if self.is_decoder: |
|
outputs = outputs + (present_key_value,) |
|
|
|
return outputs |
|
|
|
|
|
class JinaBertEncoder(nn.Module): |
|
def __init__(self, config: JinaBertConfig): |
|
super().__init__() |
|
self.config = config |
|
self.layer = nn.ModuleList( |
|
[JinaBertLayer(config) for _ in range(config.num_hidden_layers)] |
|
) |
|
self.gradient_checkpointing = False |
|
self.num_attention_heads = config.num_attention_heads |
|
self.register_buffer( |
|
"alibi", |
|
self.rebuild_alibi_tensor(size=config.max_position_embeddings), |
|
persistent=False, |
|
) |
|
|
|
def rebuild_alibi_tensor( |
|
self, size: int, device: Optional[Union[torch.device, str]] = None |
|
): |
|
|
|
|
|
|
|
|
|
|
|
n_heads = self.num_attention_heads |
|
|
|
def _get_alibi_head_slopes(n_heads: int) -> List[float]: |
|
def get_slopes_power_of_2(n): |
|
start = 2 ** (-(2 ** -(math.log2(n) - 3))) |
|
ratio = start |
|
return [start * ratio**i for i in range(n)] |
|
|
|
if math.log2(n_heads).is_integer(): |
|
return get_slopes_power_of_2( |
|
n_heads |
|
) |
|
else: |
|
closest_power_of_2 = 2 ** math.floor( |
|
math.log2(n_heads) |
|
) |
|
return ( |
|
get_slopes_power_of_2(closest_power_of_2) |
|
+ _get_alibi_head_slopes(2 * closest_power_of_2)[0::2][ |
|
: n_heads - closest_power_of_2 |
|
] |
|
) |
|
|
|
context_position = torch.arange(size, device=device)[:, None] |
|
memory_position = torch.arange(size, device=device)[None, :] |
|
relative_position = torch.abs(memory_position - context_position) |
|
|
|
relative_position = relative_position.unsqueeze(0).expand(n_heads, -1, -1) |
|
slopes = torch.Tensor(_get_alibi_head_slopes(n_heads)).to(device) * -1 |
|
alibi = slopes.unsqueeze(1).unsqueeze(1) * relative_position |
|
|
|
alibi = alibi.unsqueeze(0) |
|
assert alibi.shape == torch.Size([1, n_heads, size, size]) |
|
|
|
self._current_alibi_size = size |
|
return alibi |
|
|
|
def forward( |
|
self, |
|
hidden_states: torch.Tensor, |
|
attention_mask: Optional[torch.FloatTensor] = None, |
|
head_mask: Optional[torch.FloatTensor] = None, |
|
encoder_hidden_states: Optional[torch.FloatTensor] = None, |
|
encoder_attention_mask: Optional[torch.FloatTensor] = None, |
|
past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None, |
|
use_cache: Optional[bool] = None, |
|
output_attentions: Optional[bool] = False, |
|
output_hidden_states: Optional[bool] = False, |
|
return_dict: Optional[bool] = True, |
|
) -> Union[Tuple[torch.Tensor], BaseModelOutputWithPastAndCrossAttentions]: |
|
all_hidden_states = () if output_hidden_states else None |
|
all_self_attentions = () if output_attentions else None |
|
all_cross_attentions = ( |
|
() if output_attentions and self.config.add_cross_attention else None |
|
) |
|
|
|
|
|
_, seqlen, _ = hidden_states.size() |
|
if self._current_alibi_size < seqlen: |
|
|
|
warnings.warn( |
|
f'Increasing alibi size from {self._current_alibi_size} to {seqlen}.' |
|
) |
|
self.register_buffer( |
|
"alibi", |
|
self.rebuild_alibi_tensor(size=seqlen, device=hidden_states.device).to( |
|
hidden_states.dtype |
|
), |
|
persistent=False, |
|
) |
|
elif self.alibi.device != hidden_states.device: |
|
|
|
self.alibi = self.alibi.to(hidden_states.device) |
|
|
|
alibi_bias = self.alibi[:, :, :seqlen, :seqlen] |
|
if self.gradient_checkpointing and self.training: |
|
if use_cache: |
|
logger.warning_once( |
|
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..." |
|
) |
|
use_cache = False |
|
|
|
next_decoder_cache = () if use_cache else None |
|
for i, layer_module in enumerate(self.layer): |
|
if output_hidden_states: |
|
all_hidden_states = all_hidden_states + (hidden_states,) |
|
|
|
layer_head_mask = head_mask[i] if head_mask is not None else None |
|
past_key_value = past_key_values[i] if past_key_values is not None else None |
|
|
|
if self.gradient_checkpointing and self.training: |
|
|
|
def create_custom_forward(module): |
|
def custom_forward(*inputs): |
|
return module(*inputs, past_key_value, output_attentions) |
|
|
|
return custom_forward |
|
|
|
layer_outputs = torch.utils.checkpoint.checkpoint( |
|
create_custom_forward(layer_module), |
|
hidden_states, |
|
attention_mask, |
|
layer_head_mask, |
|
encoder_hidden_states, |
|
encoder_attention_mask, |
|
alibi_bias, |
|
) |
|
else: |
|
layer_outputs = layer_module( |
|
hidden_states, |
|
attention_mask, |
|
layer_head_mask, |
|
encoder_hidden_states, |
|
encoder_attention_mask, |
|
alibi_bias, |
|
past_key_value, |
|
output_attentions, |
|
) |
|
|
|
hidden_states = layer_outputs[0] |
|
if use_cache: |
|
next_decoder_cache += (layer_outputs[-1],) |
|
if output_attentions: |
|
all_self_attentions = all_self_attentions + (layer_outputs[1],) |
|
if self.config.add_cross_attention: |
|
all_cross_attentions = all_cross_attentions + (layer_outputs[2],) |
|
|
|
if output_hidden_states: |
|
all_hidden_states = all_hidden_states + (hidden_states,) |
|
|
|
if not return_dict: |
|
return tuple( |
|
v |
|
for v in [ |
|
hidden_states, |
|
next_decoder_cache, |
|
all_hidden_states, |
|
all_self_attentions, |
|
all_cross_attentions, |
|
] |
|
if v is not None |
|
) |
|
return BaseModelOutputWithPastAndCrossAttentions( |
|
last_hidden_state=hidden_states, |
|
past_key_values=next_decoder_cache, |
|
hidden_states=all_hidden_states, |
|
attentions=all_self_attentions, |
|
cross_attentions=all_cross_attentions, |
|
) |
|
|
|
|
|
class JinaBertPooler(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.dense = nn.Linear(config.hidden_size, config.hidden_size) |
|
self.activation = nn.Tanh() |
|
|
|
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: |
|
|
|
|
|
first_token_tensor = hidden_states[:, 0] |
|
pooled_output = self.dense(first_token_tensor) |
|
pooled_output = self.activation(pooled_output) |
|
return pooled_output |
|
|
|
|
|
class JinaBertPredictionHeadTransform(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.dense = nn.Linear(config.hidden_size, config.hidden_size) |
|
if isinstance(config.hidden_act, str): |
|
self.transform_act_fn = ACT2FN[config.hidden_act] |
|
else: |
|
self.transform_act_fn = config.hidden_act |
|
self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps) |
|
|
|
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: |
|
hidden_states = self.dense(hidden_states) |
|
hidden_states = self.transform_act_fn(hidden_states) |
|
hidden_states = self.LayerNorm(hidden_states) |
|
return hidden_states |
|
|
|
|
|
class JinaBertLMPredictionHead(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.transform = JinaBertPredictionHeadTransform(config) |
|
|
|
|
|
|
|
self.decoder = nn.Linear(config.hidden_size, config.vocab_size, bias=False) |
|
|
|
self.bias = nn.Parameter(torch.zeros(config.vocab_size)) |
|
|
|
|
|
self.decoder.bias = self.bias |
|
|
|
def forward(self, hidden_states): |
|
hidden_states = self.transform(hidden_states) |
|
hidden_states = self.decoder(hidden_states) |
|
return hidden_states |
|
|
|
|
|
class JinaBertOnlyMLMHead(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.predictions = JinaBertLMPredictionHead(config) |
|
|
|
def forward(self, sequence_output: torch.Tensor) -> torch.Tensor: |
|
prediction_scores = self.predictions(sequence_output) |
|
return prediction_scores |
|
|
|
|
|
class JinaBertOnlyNSPHead(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.seq_relationship = nn.Linear(config.hidden_size, 2) |
|
|
|
def forward(self, pooled_output): |
|
seq_relationship_score = self.seq_relationship(pooled_output) |
|
return seq_relationship_score |
|
|
|
|
|
class JinaBertPreTrainingHeads(nn.Module): |
|
def __init__(self, config): |
|
super().__init__() |
|
self.predictions = JinaBertLMPredictionHead(config) |
|
self.seq_relationship = nn.Linear(config.hidden_size, 2) |
|
|
|
def forward(self, sequence_output, pooled_output): |
|
prediction_scores = self.predictions(sequence_output) |
|
seq_relationship_score = self.seq_relationship(pooled_output) |
|
return prediction_scores, seq_relationship_score |
|
|
|
|
|
class JinaBertPreTrainedModel(PreTrainedModel): |
|
""" |
|
An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained |
|
models. |
|
""" |
|
|
|
config_class = JinaBertConfig |
|
load_tf_weights = load_tf_weights_in_bert |
|
base_model_prefix = "bert" |
|
supports_gradient_checkpointing = True |
|
_no_split_modules = ["JinaBertLayer"] |
|
|
|
def _init_weights(self, module): |
|
"""Initialize the weights""" |
|
if isinstance(module, nn.Linear): |
|
|
|
|
|
module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) |
|
if module.bias is not None: |
|
module.bias.data.zero_() |
|
elif isinstance(module, nn.Embedding): |
|
module.weight.data.normal_(mean=0.0, std=self.config.initializer_range) |
|
if module.padding_idx is not None: |
|
module.weight.data[module.padding_idx].zero_() |
|
elif isinstance(module, nn.LayerNorm): |
|
module.bias.data.zero_() |
|
module.weight.data.fill_(1.0) |
|
|
|
def _set_gradient_checkpointing(self, module, value=False): |
|
if isinstance(module, JinaBertEncoder): |
|
module.gradient_checkpointing = value |
|
|
|
|
|
@dataclass |
|
class JinaBertForPreTrainingOutput(ModelOutput): |
|
""" |
|
Output type of [`BertForPreTraining`]. |
|
|
|
Args: |
|
loss (*optional*, returned when `labels` is provided, `torch.FloatTensor` of shape `(1,)`): |
|
Total loss as the sum of the masked language modeling loss and the next sequence prediction |
|
(classification) loss. |
|
prediction_logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`): |
|
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). |
|
seq_relationship_logits (`torch.FloatTensor` of shape `(batch_size, 2)`): |
|
Prediction scores of the next sequence prediction (classification) head (scores of True/False continuation |
|
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. |
|
""" |
|
|
|
loss: Optional[torch.FloatTensor] = None |
|
prediction_logits: torch.FloatTensor = None |
|
seq_relationship_logits: torch.FloatTensor = None |
|
hidden_states: Optional[Tuple[torch.FloatTensor]] = None |
|
attentions: Optional[Tuple[torch.FloatTensor]] = None |
|
|
|
|
|
BERT_START_DOCSTRING = r""" |
|
|
|
This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the |
|
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads |
|
etc.) |
|
|
|
This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. |
|
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage |
|
and behavior. |
|
|
|
Parameters: |
|
config ([`BertConfig`]): 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 [`~PreTrainedModel.from_pretrained`] method to load the model weights. |
|
""" |
|
|
|
BERT_INPUTS_DOCSTRING = r""" |
|
Args: |
|
input_ids (`torch.LongTensor` of shape `({0})`): |
|
Indices of input sequence tokens in the vocabulary. |
|
|
|
Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and |
|
[`PreTrainedTokenizer.__call__`] for details. |
|
|
|
[What are input IDs?](../glossary#input-ids) |
|
attention_mask (`torch.FloatTensor` of shape `({0})`, *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?](../glossary#attention-mask) |
|
token_type_ids (`torch.LongTensor` of shape `({0})`, *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?](../glossary#token-type-ids) |
|
position_ids (`torch.LongTensor` of shape `({0})`, *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?](../glossary#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 `({0}, 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 [`~utils.ModelOutput`] instead of a plain tuple. |
|
""" |
|
|
|
|
|
@add_start_docstrings( |
|
"The bare Bert Model transformer outputting raw hidden-states without any specific head on top.", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertModel(JinaBertPreTrainedModel): |
|
""" |
|
|
|
The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of |
|
cross-attention is added between the self-attention layers, following the architecture described in [Attention is |
|
all you need](https://arxiv.org/abs/1706.03762) by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, |
|
Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin. |
|
|
|
To behave as an decoder the model needs to be initialized with the `is_decoder` argument of the configuration set |
|
to `True`. To be used in a Seq2Seq model, the model needs to initialized with both `is_decoder` argument and |
|
`add_cross_attention` set to `True`; an `encoder_hidden_states` is then expected as an input to the forward pass. |
|
""" |
|
|
|
def __init__(self, config: JinaBertConfig, add_pooling_layer=True): |
|
super().__init__(config) |
|
self.config = config |
|
|
|
self.emb_pooler = config.emb_pooler |
|
self._name_or_path = config._name_or_path |
|
if self.emb_pooler: |
|
from transformers import AutoTokenizer |
|
|
|
self.tokenizer = AutoTokenizer.from_pretrained(config._name_or_path) |
|
|
|
self.embeddings = JinaBertEmbeddings(config) |
|
self.encoder = JinaBertEncoder(config) |
|
|
|
self.pooler = JinaBertPooler(config) if add_pooling_layer else None |
|
|
|
|
|
self.post_init() |
|
|
|
@torch.inference_mode() |
|
def encode( |
|
self: 'JinaBertModel', |
|
sentences: Union[str, List[str]], |
|
batch_size: int = 32, |
|
show_progress_bar: Optional[bool] = None, |
|
output_value: str = 'sentence_embedding', |
|
convert_to_numpy: bool = True, |
|
convert_to_tensor: bool = False, |
|
device: Optional[torch.device] = None, |
|
normalize_embeddings: bool = False, |
|
**tokenizer_kwargs, |
|
) -> Union[List[torch.Tensor], np.ndarray, torch.Tensor]: |
|
""" |
|
Computes sentence embeddings |
|
|
|
Args: |
|
sentences(`str` or `List[str]`): |
|
Sentence or sentences to be encoded |
|
batch_size(`int`, *optional*, defaults to 32): |
|
Batch size for the computation |
|
show_progress_bar(`bool`, *optional*, defaults to None): |
|
Show a progress bar when encoding sentences. |
|
If set to None, progress bar is only shown when `logger.level == logging.INFO` or `logger.level == logging.DEBUG`. |
|
output_value(`str`, *optional*, defaults to 'sentence_embedding'): |
|
Default sentence_embedding, to get sentence embeddings. |
|
Can be set to token_embeddings to get wordpiece token embeddings. |
|
Set to None, to get all output values |
|
convert_to_numpy(`bool`, *optional*, defaults to True): |
|
If true, the output is a list of numpy vectors. |
|
Else, it is a list of pytorch tensors. |
|
convert_to_tensor(`bool`, *optional*, defaults to False): |
|
If true, you get one large tensor as return. |
|
Overwrites any setting from convert_to_numpy |
|
device(`torch.device`, *optional*, defaults to None): |
|
Which torch.device to use for the computation |
|
normalize_embeddings(`bool`, *optional*, defaults to False): |
|
If set to true, returned vectors will have length 1. In that case, the faster dot-product (util.dot_score) instead of cosine similarity can be used. |
|
tokenizer_kwargs(`Dict[str, Any]`, *optional*, defaults to {}): |
|
Keyword arguments for the tokenizer |
|
|
|
Returns: |
|
By default, a list of tensors is returned. |
|
If convert_to_tensor, a stacked tensor is returned. |
|
If convert_to_numpy, a numpy matrix is returned. |
|
""" |
|
if not self.emb_pooler: |
|
warnings.warn("No emb_pooler specified, defaulting to mean pooling.") |
|
self.emb_pooler = 'mean' |
|
from transformers import AutoTokenizer |
|
|
|
self.tokenizer = AutoTokenizer.from_pretrained(self._name_or_path) |
|
is_training = self.training |
|
self.eval() |
|
|
|
if show_progress_bar is None: |
|
show_progress_bar = ( |
|
logger.getEffectiveLevel() == logging.INFO |
|
or logger.getEffectiveLevel() == logging.DEBUG |
|
) |
|
|
|
if convert_to_tensor: |
|
convert_to_numpy = False |
|
|
|
if output_value != 'sentence_embedding': |
|
convert_to_tensor = False |
|
convert_to_numpy = False |
|
|
|
input_was_string = False |
|
if isinstance(sentences, str) or not hasattr(sentences, '__len__'): |
|
sentences = [sentences] |
|
input_was_string = True |
|
|
|
if device is not None: |
|
self.to(device) |
|
|
|
|
|
permutation = np.argsort([-len(i) for i in sentences]) |
|
inverse_permutation = np.argsort(permutation) |
|
sentences = [sentences[idx] for idx in permutation] |
|
|
|
tokenizer_kwargs['padding'] = tokenizer_kwargs.get('padding', True) |
|
tokenizer_kwargs['max_length'] = tokenizer_kwargs.get('max_length', 8192) |
|
tokenizer_kwargs['truncation'] = tokenizer_kwargs.get('truncation', True) |
|
|
|
all_embeddings = [] |
|
|
|
if has_tqdm: |
|
range_iter = trange( |
|
0, |
|
len(sentences), |
|
batch_size, |
|
desc="Encoding", |
|
disable=not show_progress_bar, |
|
) |
|
else: |
|
range_iter = range(0, len(sentences), batch_size) |
|
|
|
for i in range_iter: |
|
encoded_input = self.tokenizer( |
|
sentences[i : i + batch_size], |
|
return_tensors='pt', |
|
**tokenizer_kwargs, |
|
).to(self.device) |
|
token_embs = self.forward(**encoded_input)[0] |
|
|
|
|
|
token_embs = token_embs.float() |
|
|
|
if output_value == 'token_embeddings': |
|
raise NotImplementedError |
|
elif output_value is None: |
|
raise NotImplementedError |
|
else: |
|
embeddings = self.mean_pooling( |
|
token_embs, encoded_input['attention_mask'] |
|
) |
|
|
|
if normalize_embeddings: |
|
embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1) |
|
|
|
if convert_to_numpy: |
|
embeddings = embeddings.cpu() |
|
all_embeddings.extend(embeddings) |
|
|
|
all_embeddings = [all_embeddings[idx] for idx in inverse_permutation] |
|
|
|
if convert_to_tensor: |
|
all_embeddings = torch.stack(all_embeddings) |
|
elif convert_to_numpy: |
|
all_embeddings = np.asarray([emb.numpy() for emb in all_embeddings]) |
|
|
|
if input_was_string: |
|
all_embeddings = all_embeddings[0] |
|
|
|
self.train(is_training) |
|
return all_embeddings |
|
|
|
def mean_pooling( |
|
self, token_embeddings: torch.Tensor, attention_mask: torch.Tensor |
|
): |
|
input_mask_expanded = ( |
|
attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() |
|
) |
|
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp( |
|
input_mask_expanded.sum(1), min=1e-9 |
|
) |
|
|
|
def get_input_embeddings(self): |
|
return self.embeddings.word_embeddings |
|
|
|
def set_input_embeddings(self, value): |
|
self.embeddings.word_embeddings = value |
|
|
|
def _prune_heads(self, heads_to_prune): |
|
""" |
|
Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base |
|
class PreTrainedModel |
|
""" |
|
for layer, heads in heads_to_prune.items(): |
|
self.encoder.layer[layer].attention.prune_heads(heads) |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_DOC, |
|
output_type=BaseModelOutputWithPoolingAndCrossAttentions, |
|
config_class=_CONFIG_FOR_DOC, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
encoder_hidden_states: Optional[torch.Tensor] = None, |
|
encoder_attention_mask: Optional[torch.Tensor] = None, |
|
past_key_values: Optional[List[torch.FloatTensor]] = None, |
|
use_cache: Optional[bool] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], BaseModelOutputWithPoolingAndCrossAttentions]: |
|
r""" |
|
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`). |
|
""" |
|
output_attentions = ( |
|
output_attentions |
|
if output_attentions is not None |
|
else self.config.output_attentions |
|
) |
|
output_hidden_states = ( |
|
output_hidden_states |
|
if output_hidden_states is not None |
|
else self.config.output_hidden_states |
|
) |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
if self.config.is_decoder: |
|
use_cache = use_cache if use_cache is not None else self.config.use_cache |
|
else: |
|
use_cache = False |
|
|
|
if input_ids is not None and inputs_embeds is not None: |
|
raise ValueError( |
|
"You cannot specify both input_ids and inputs_embeds at the same time" |
|
) |
|
elif input_ids is not None: |
|
|
|
input_shape = input_ids.size() |
|
elif inputs_embeds is not None: |
|
input_shape = inputs_embeds.size()[:-1] |
|
else: |
|
raise ValueError("You have to specify either input_ids or inputs_embeds") |
|
|
|
batch_size, seq_length = input_shape |
|
device = input_ids.device if input_ids is not None else inputs_embeds.device |
|
|
|
|
|
past_key_values_length = ( |
|
past_key_values[0][0].shape[2] if past_key_values is not None else 0 |
|
) |
|
|
|
if attention_mask is None: |
|
attention_mask = torch.ones( |
|
((batch_size, seq_length + past_key_values_length)), device=device |
|
) |
|
|
|
if token_type_ids is None: |
|
if hasattr(self.embeddings, "token_type_ids"): |
|
buffered_token_type_ids = self.embeddings.token_type_ids[:, :seq_length] |
|
buffered_token_type_ids_expanded = buffered_token_type_ids.expand( |
|
batch_size, seq_length |
|
) |
|
token_type_ids = buffered_token_type_ids_expanded |
|
else: |
|
token_type_ids = torch.zeros( |
|
input_shape, dtype=torch.long, device=device |
|
) |
|
|
|
|
|
|
|
extended_attention_mask: torch.Tensor = self.get_extended_attention_mask( |
|
attention_mask, input_shape |
|
) |
|
|
|
|
|
|
|
if self.config.is_decoder and encoder_hidden_states is not None: |
|
( |
|
encoder_batch_size, |
|
encoder_sequence_length, |
|
_, |
|
) = encoder_hidden_states.size() |
|
encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length) |
|
if encoder_attention_mask is None: |
|
encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device) |
|
encoder_extended_attention_mask = self.invert_attention_mask( |
|
encoder_attention_mask |
|
) |
|
else: |
|
encoder_extended_attention_mask = None |
|
|
|
|
|
|
|
|
|
|
|
|
|
head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers) |
|
|
|
embedding_output = self.embeddings( |
|
input_ids=input_ids, |
|
position_ids=position_ids, |
|
token_type_ids=token_type_ids, |
|
inputs_embeds=inputs_embeds, |
|
past_key_values_length=past_key_values_length, |
|
) |
|
encoder_outputs = self.encoder( |
|
embedding_output, |
|
attention_mask=extended_attention_mask, |
|
head_mask=head_mask, |
|
encoder_hidden_states=encoder_hidden_states, |
|
encoder_attention_mask=encoder_extended_attention_mask, |
|
past_key_values=past_key_values, |
|
use_cache=use_cache, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
sequence_output = encoder_outputs[0] |
|
pooled_output = ( |
|
self.pooler(sequence_output) if self.pooler is not None else None |
|
) |
|
|
|
if not return_dict: |
|
return (sequence_output, pooled_output) + encoder_outputs[1:] |
|
|
|
return BaseModelOutputWithPoolingAndCrossAttentions( |
|
last_hidden_state=sequence_output, |
|
pooler_output=pooled_output, |
|
past_key_values=encoder_outputs.past_key_values, |
|
hidden_states=encoder_outputs.hidden_states, |
|
attentions=encoder_outputs.attentions, |
|
cross_attentions=encoder_outputs.cross_attentions, |
|
) |
|
|
|
|
|
@add_start_docstrings( |
|
""" |
|
Bert Model with two heads on top as done during the pretraining: a `masked language modeling` head and a `next |
|
sentence prediction (classification)` head. |
|
""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertForPreTraining(JinaBertPreTrainedModel): |
|
_tied_weights_keys = ["predictions.decoder.bias", "cls.predictions.decoder.weight"] |
|
|
|
def __init__(self, config): |
|
super().__init__(config) |
|
|
|
self.bert = JinaBertModel(config) |
|
self.cls = JinaBertPreTrainingHeads(config) |
|
|
|
|
|
self.post_init() |
|
|
|
def get_output_embeddings(self): |
|
return self.cls.predictions.decoder |
|
|
|
def set_output_embeddings(self, new_embeddings): |
|
self.cls.predictions.decoder = new_embeddings |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@replace_return_docstrings( |
|
output_type=JinaBertForPreTrainingOutput, config_class=_CONFIG_FOR_DOC |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
next_sentence_label: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], JinaBertForPreTrainingOutput]: |
|
r""" |
|
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): |
|
Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., |
|
config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), |
|
the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]` |
|
next_sentence_label (`torch.LongTensor` of shape `(batch_size,)`, *optional*): |
|
Labels for computing the next sequence prediction (classification) loss. Input should be a sequence |
|
pair (see `input_ids` docstring) Indices should be in `[0, 1]`: |
|
|
|
- 0 indicates sequence B is a continuation of sequence A, |
|
- 1 indicates sequence B is a random sequence. |
|
kwargs (`Dict[str, any]`, optional, defaults to *{}*): |
|
Used to hide legacy arguments that have been deprecated. |
|
|
|
Returns: |
|
""" |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
sequence_output, pooled_output = outputs[:2] |
|
prediction_scores, seq_relationship_score = self.cls( |
|
sequence_output, pooled_output |
|
) |
|
|
|
total_loss = None |
|
if labels is not None and next_sentence_label is not None: |
|
loss_fct = CrossEntropyLoss() |
|
masked_lm_loss = loss_fct( |
|
prediction_scores.view(-1, self.config.vocab_size), labels.view(-1) |
|
) |
|
next_sentence_loss = loss_fct( |
|
seq_relationship_score.view(-1, 2), next_sentence_label.view(-1) |
|
) |
|
total_loss = masked_lm_loss + next_sentence_loss |
|
|
|
if not return_dict: |
|
output = (prediction_scores, seq_relationship_score) + outputs[2:] |
|
return ((total_loss,) + output) if total_loss is not None else output |
|
|
|
return JinaBertForPreTrainingOutput( |
|
loss=total_loss, |
|
prediction_logits=prediction_scores, |
|
seq_relationship_logits=seq_relationship_score, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
|
|
@add_start_docstrings( |
|
"""JinaBert Model with a `language modeling` head on top for CLM fine-tuning.""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertLMHeadModel(JinaBertPreTrainedModel): |
|
_tied_weights_keys = ["predictions.decoder.bias", "cls.predictions.decoder.weight"] |
|
|
|
def __init__(self, config): |
|
super().__init__(config) |
|
|
|
if not config.is_decoder: |
|
logger.warning( |
|
"If you want to use `JinaBertLMHeadModel` as a standalone, add `is_decoder=True.`" |
|
) |
|
|
|
self.bert = JinaBertModel(config, add_pooling_layer=False) |
|
self.cls = JinaBertOnlyMLMHead(config) |
|
|
|
|
|
self.post_init() |
|
|
|
def get_output_embeddings(self): |
|
return self.cls.predictions.decoder |
|
|
|
def set_output_embeddings(self, new_embeddings): |
|
self.cls.predictions.decoder = new_embeddings |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_DOC, |
|
output_type=CausalLMOutputWithCrossAttentions, |
|
config_class=_CONFIG_FOR_DOC, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
encoder_hidden_states: Optional[torch.Tensor] = None, |
|
encoder_attention_mask: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
past_key_values: Optional[List[torch.Tensor]] = None, |
|
use_cache: Optional[bool] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], CausalLMOutputWithCrossAttentions]: |
|
r""" |
|
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**. |
|
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): |
|
Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in |
|
`[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are |
|
ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]` |
|
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`). |
|
""" |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
if labels is not None: |
|
use_cache = False |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
encoder_hidden_states=encoder_hidden_states, |
|
encoder_attention_mask=encoder_attention_mask, |
|
past_key_values=past_key_values, |
|
use_cache=use_cache, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
sequence_output = outputs[0] |
|
prediction_scores = self.cls(sequence_output) |
|
|
|
lm_loss = None |
|
if labels is not None: |
|
|
|
shifted_prediction_scores = prediction_scores[:, :-1, :].contiguous() |
|
labels = labels[:, 1:].contiguous() |
|
loss_fct = CrossEntropyLoss() |
|
lm_loss = loss_fct( |
|
shifted_prediction_scores.view(-1, self.config.vocab_size), |
|
labels.view(-1), |
|
) |
|
|
|
if not return_dict: |
|
output = (prediction_scores,) + outputs[2:] |
|
return ((lm_loss,) + output) if lm_loss is not None else output |
|
|
|
return CausalLMOutputWithCrossAttentions( |
|
loss=lm_loss, |
|
logits=prediction_scores, |
|
past_key_values=outputs.past_key_values, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
cross_attentions=outputs.cross_attentions, |
|
) |
|
|
|
def prepare_inputs_for_generation( |
|
self, |
|
input_ids, |
|
past_key_values=None, |
|
attention_mask=None, |
|
use_cache=True, |
|
**model_kwargs, |
|
): |
|
input_shape = input_ids.shape |
|
|
|
if attention_mask is None: |
|
attention_mask = input_ids.new_ones(input_shape) |
|
|
|
|
|
if past_key_values is not None: |
|
input_ids = input_ids[:, -1:] |
|
|
|
return { |
|
"input_ids": input_ids, |
|
"attention_mask": attention_mask, |
|
"past_key_values": past_key_values, |
|
"use_cache": use_cache, |
|
} |
|
|
|
def _reorder_cache(self, past_key_values, beam_idx): |
|
reordered_past = () |
|
for layer_past in past_key_values: |
|
reordered_past += ( |
|
tuple( |
|
past_state.index_select(0, beam_idx) for past_state in layer_past |
|
), |
|
) |
|
return reordered_past |
|
|
|
|
|
@add_start_docstrings( |
|
"""JinaBert Model with a `language modeling` head on top.""", BERT_START_DOCSTRING |
|
) |
|
class JinaBertForMaskedLM(JinaBertPreTrainedModel): |
|
_tied_weights_keys = ["predictions.decoder.bias", "cls.predictions.decoder.weight"] |
|
|
|
def __init__(self, config): |
|
super().__init__(config) |
|
|
|
if config.is_decoder: |
|
logger.warning( |
|
"If you want to use `JinaBertForMaskedLM` make sure `config.is_decoder=False` for " |
|
"bi-directional self-attention." |
|
) |
|
|
|
self.bert = JinaBertModel(config, add_pooling_layer=False) |
|
self.cls = JinaBertOnlyMLMHead(config) |
|
|
|
|
|
self.post_init() |
|
|
|
def get_output_embeddings(self): |
|
return self.cls.predictions.decoder |
|
|
|
def set_output_embeddings(self, new_embeddings): |
|
self.cls.predictions.decoder = new_embeddings |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_DOC, |
|
output_type=MaskedLMOutput, |
|
config_class=_CONFIG_FOR_DOC, |
|
expected_output="'paris'", |
|
expected_loss=0.88, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
encoder_hidden_states: Optional[torch.Tensor] = None, |
|
encoder_attention_mask: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], MaskedLMOutput]: |
|
r""" |
|
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): |
|
Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ..., |
|
config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the |
|
loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]` |
|
""" |
|
|
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
encoder_hidden_states=encoder_hidden_states, |
|
encoder_attention_mask=encoder_attention_mask, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
sequence_output = outputs[0] |
|
prediction_scores = self.cls(sequence_output) |
|
|
|
masked_lm_loss = None |
|
if labels is not None: |
|
loss_fct = CrossEntropyLoss() |
|
masked_lm_loss = loss_fct( |
|
prediction_scores.view(-1, self.config.vocab_size), labels.view(-1) |
|
) |
|
|
|
if not return_dict: |
|
output = (prediction_scores,) + outputs[2:] |
|
return ( |
|
((masked_lm_loss,) + output) if masked_lm_loss is not None else output |
|
) |
|
|
|
return MaskedLMOutput( |
|
loss=masked_lm_loss, |
|
logits=prediction_scores, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
def prepare_inputs_for_generation( |
|
self, input_ids, attention_mask=None, **model_kwargs |
|
): |
|
input_shape = input_ids.shape |
|
effective_batch_size = input_shape[0] |
|
|
|
|
|
if self.config.pad_token_id is None: |
|
raise ValueError("The PAD token should be defined for generation") |
|
|
|
attention_mask = torch.cat( |
|
[attention_mask, attention_mask.new_zeros((attention_mask.shape[0], 1))], |
|
dim=-1, |
|
) |
|
dummy_token = torch.full( |
|
(effective_batch_size, 1), |
|
self.config.pad_token_id, |
|
dtype=torch.long, |
|
device=input_ids.device, |
|
) |
|
input_ids = torch.cat([input_ids, dummy_token], dim=1) |
|
|
|
return {"input_ids": input_ids, "attention_mask": attention_mask} |
|
|
|
|
|
@add_start_docstrings( |
|
"""JinaBert Model with a `next sentence prediction (classification)` head on top.""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertForNextSentencePrediction(JinaBertPreTrainedModel): |
|
def __init__(self, config): |
|
super().__init__(config) |
|
|
|
self.bert = JinaBertModel(config) |
|
self.cls = JinaBertOnlyNSPHead(config) |
|
|
|
|
|
self.post_init() |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@replace_return_docstrings( |
|
output_type=NextSentencePredictorOutput, config_class=_CONFIG_FOR_DOC |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
**kwargs, |
|
) -> Union[Tuple[torch.Tensor], NextSentencePredictorOutput]: |
|
r""" |
|
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): |
|
Labels for computing the next sequence prediction (classification) loss. Input should be a sequence pair |
|
(see `input_ids` docstring). Indices should be in `[0, 1]`: |
|
|
|
- 0 indicates sequence B is a continuation of sequence A, |
|
- 1 indicates sequence B is a random sequence. |
|
|
|
Returns: |
|
""" |
|
|
|
if "next_sentence_label" in kwargs: |
|
warnings.warn( |
|
"The `next_sentence_label` argument is deprecated and will be removed in a future version, use" |
|
" `labels` instead.", |
|
FutureWarning, |
|
) |
|
labels = kwargs.pop("next_sentence_label") |
|
|
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
pooled_output = outputs[1] |
|
|
|
seq_relationship_scores = self.cls(pooled_output) |
|
|
|
next_sentence_loss = None |
|
if labels is not None: |
|
loss_fct = CrossEntropyLoss() |
|
next_sentence_loss = loss_fct( |
|
seq_relationship_scores.view(-1, 2), labels.view(-1) |
|
) |
|
|
|
if not return_dict: |
|
output = (seq_relationship_scores,) + outputs[2:] |
|
return ( |
|
((next_sentence_loss,) + output) |
|
if next_sentence_loss is not None |
|
else output |
|
) |
|
|
|
return NextSentencePredictorOutput( |
|
loss=next_sentence_loss, |
|
logits=seq_relationship_scores, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
|
|
@add_start_docstrings( |
|
""" |
|
JinaBert Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled |
|
output) e.g. for GLUE tasks. |
|
""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertForSequenceClassification(JinaBertPreTrainedModel): |
|
def __init__(self, config): |
|
super().__init__(config) |
|
self.num_labels = config.num_labels |
|
self.config = config |
|
|
|
self.bert = JinaBertModel(config) |
|
classifier_dropout = ( |
|
config.classifier_dropout |
|
if config.classifier_dropout is not None |
|
else config.hidden_dropout_prob |
|
) |
|
self.dropout = nn.Dropout(classifier_dropout) |
|
self.classifier = nn.Linear(config.hidden_size, config.num_labels) |
|
|
|
|
|
self.post_init() |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION, |
|
output_type=SequenceClassifierOutput, |
|
config_class=_CONFIG_FOR_DOC, |
|
expected_output=_SEQ_CLASS_EXPECTED_OUTPUT, |
|
expected_loss=_SEQ_CLASS_EXPECTED_LOSS, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]: |
|
r""" |
|
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): |
|
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., |
|
config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If |
|
`config.num_labels > 1` a classification loss is computed (Cross-Entropy). |
|
""" |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
pooled_output = outputs[1] |
|
|
|
pooled_output = self.dropout(pooled_output) |
|
logits = self.classifier(pooled_output) |
|
|
|
loss = None |
|
if labels is not None: |
|
if self.config.problem_type is None: |
|
if self.num_labels == 1: |
|
self.config.problem_type = "regression" |
|
elif self.num_labels > 1 and ( |
|
labels.dtype == torch.long or labels.dtype == torch.int |
|
): |
|
self.config.problem_type = "single_label_classification" |
|
else: |
|
self.config.problem_type = "multi_label_classification" |
|
|
|
if self.config.problem_type == "regression": |
|
loss_fct = MSELoss() |
|
if self.num_labels == 1: |
|
loss = loss_fct(logits.squeeze(), labels.squeeze()) |
|
else: |
|
loss = loss_fct(logits, labels) |
|
elif self.config.problem_type == "single_label_classification": |
|
loss_fct = CrossEntropyLoss() |
|
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) |
|
elif self.config.problem_type == "multi_label_classification": |
|
loss_fct = BCEWithLogitsLoss() |
|
loss = loss_fct(logits, labels) |
|
if not return_dict: |
|
output = (logits,) + outputs[2:] |
|
return ((loss,) + output) if loss is not None else output |
|
|
|
return SequenceClassifierOutput( |
|
loss=loss, |
|
logits=logits, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
|
|
@add_start_docstrings( |
|
""" |
|
JinaBert Model with a multiple choice classification head on top (a linear layer on top of the pooled output and a |
|
softmax) e.g. for RocStories/SWAG tasks. |
|
""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertForMultipleChoice(JinaBertPreTrainedModel): |
|
def __init__(self, config): |
|
super().__init__(config) |
|
|
|
self.bert = JinaBertModel(config) |
|
classifier_dropout = ( |
|
config.classifier_dropout |
|
if config.classifier_dropout is not None |
|
else config.hidden_dropout_prob |
|
) |
|
self.dropout = nn.Dropout(classifier_dropout) |
|
self.classifier = nn.Linear(config.hidden_size, 1) |
|
|
|
|
|
self.post_init() |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, num_choices, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_DOC, |
|
output_type=MultipleChoiceModelOutput, |
|
config_class=_CONFIG_FOR_DOC, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], MultipleChoiceModelOutput]: |
|
r""" |
|
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): |
|
Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., |
|
num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See |
|
`input_ids` above) |
|
""" |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
num_choices = ( |
|
input_ids.shape[1] if input_ids is not None else inputs_embeds.shape[1] |
|
) |
|
|
|
input_ids = ( |
|
input_ids.view(-1, input_ids.size(-1)) if input_ids is not None else None |
|
) |
|
attention_mask = ( |
|
attention_mask.view(-1, attention_mask.size(-1)) |
|
if attention_mask is not None |
|
else None |
|
) |
|
token_type_ids = ( |
|
token_type_ids.view(-1, token_type_ids.size(-1)) |
|
if token_type_ids is not None |
|
else None |
|
) |
|
position_ids = ( |
|
position_ids.view(-1, position_ids.size(-1)) |
|
if position_ids is not None |
|
else None |
|
) |
|
inputs_embeds = ( |
|
inputs_embeds.view(-1, inputs_embeds.size(-2), inputs_embeds.size(-1)) |
|
if inputs_embeds is not None |
|
else None |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
pooled_output = outputs[1] |
|
|
|
pooled_output = self.dropout(pooled_output) |
|
logits = self.classifier(pooled_output) |
|
reshaped_logits = logits.view(-1, num_choices) |
|
|
|
loss = None |
|
if labels is not None: |
|
loss_fct = CrossEntropyLoss() |
|
loss = loss_fct(reshaped_logits, labels) |
|
|
|
if not return_dict: |
|
output = (reshaped_logits,) + outputs[2:] |
|
return ((loss,) + output) if loss is not None else output |
|
|
|
return MultipleChoiceModelOutput( |
|
loss=loss, |
|
logits=reshaped_logits, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
|
|
@add_start_docstrings( |
|
""" |
|
JinaBert Model with a token classification head on top (a linear layer on top of the hidden-states output) e.g. for |
|
Named-Entity-Recognition (NER) tasks. |
|
""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertForTokenClassification(JinaBertPreTrainedModel): |
|
def __init__(self, config): |
|
super().__init__(config) |
|
self.num_labels = config.num_labels |
|
|
|
self.bert = JinaBertModel(config, add_pooling_layer=False) |
|
classifier_dropout = ( |
|
config.classifier_dropout |
|
if config.classifier_dropout is not None |
|
else config.hidden_dropout_prob |
|
) |
|
self.dropout = nn.Dropout(classifier_dropout) |
|
self.classifier = nn.Linear(config.hidden_size, config.num_labels) |
|
|
|
|
|
self.post_init() |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION, |
|
output_type=TokenClassifierOutput, |
|
config_class=_CONFIG_FOR_DOC, |
|
expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT, |
|
expected_loss=_TOKEN_CLASS_EXPECTED_LOSS, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
labels: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], TokenClassifierOutput]: |
|
r""" |
|
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): |
|
Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`. |
|
""" |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
sequence_output = outputs[0] |
|
|
|
sequence_output = self.dropout(sequence_output) |
|
logits = self.classifier(sequence_output) |
|
|
|
loss = None |
|
if labels is not None: |
|
loss_fct = CrossEntropyLoss() |
|
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1)) |
|
|
|
if not return_dict: |
|
output = (logits,) + outputs[2:] |
|
return ((loss,) + output) if loss is not None else output |
|
|
|
return TokenClassifierOutput( |
|
loss=loss, |
|
logits=logits, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
|
|
@add_start_docstrings( |
|
""" |
|
JinaBert 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`). |
|
""", |
|
BERT_START_DOCSTRING, |
|
) |
|
class JinaBertForQuestionAnswering(JinaBertPreTrainedModel): |
|
def __init__(self, config): |
|
super().__init__(config) |
|
self.num_labels = config.num_labels |
|
|
|
self.bert = JinaBertModel(config, add_pooling_layer=False) |
|
self.qa_outputs = nn.Linear(config.hidden_size, config.num_labels) |
|
|
|
|
|
self.post_init() |
|
|
|
@add_start_docstrings_to_model_forward( |
|
BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length") |
|
) |
|
@add_code_sample_docstrings( |
|
checkpoint=_CHECKPOINT_FOR_QA, |
|
output_type=QuestionAnsweringModelOutput, |
|
config_class=_CONFIG_FOR_DOC, |
|
qa_target_start_index=_QA_TARGET_START_INDEX, |
|
qa_target_end_index=_QA_TARGET_END_INDEX, |
|
expected_output=_QA_EXPECTED_OUTPUT, |
|
expected_loss=_QA_EXPECTED_LOSS, |
|
) |
|
def forward( |
|
self, |
|
input_ids: Optional[torch.Tensor] = None, |
|
attention_mask: Optional[torch.Tensor] = None, |
|
token_type_ids: Optional[torch.Tensor] = None, |
|
position_ids: Optional[torch.Tensor] = None, |
|
head_mask: Optional[torch.Tensor] = None, |
|
inputs_embeds: Optional[torch.Tensor] = None, |
|
start_positions: Optional[torch.Tensor] = None, |
|
end_positions: Optional[torch.Tensor] = None, |
|
output_attentions: Optional[bool] = None, |
|
output_hidden_states: Optional[bool] = None, |
|
return_dict: Optional[bool] = None, |
|
) -> Union[Tuple[torch.Tensor], QuestionAnsweringModelOutput]: |
|
r""" |
|
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. |
|
""" |
|
return_dict = ( |
|
return_dict if return_dict is not None else self.config.use_return_dict |
|
) |
|
|
|
outputs = self.bert( |
|
input_ids, |
|
attention_mask=attention_mask, |
|
token_type_ids=token_type_ids, |
|
position_ids=position_ids, |
|
head_mask=head_mask, |
|
inputs_embeds=inputs_embeds, |
|
output_attentions=output_attentions, |
|
output_hidden_states=output_hidden_states, |
|
return_dict=return_dict, |
|
) |
|
|
|
sequence_output = outputs[0] |
|
|
|
logits = self.qa_outputs(sequence_output) |
|
start_logits, end_logits = logits.split(1, dim=-1) |
|
start_logits = start_logits.squeeze(-1).contiguous() |
|
end_logits = end_logits.squeeze(-1).contiguous() |
|
|
|
total_loss = None |
|
if start_positions is not None and end_positions is not None: |
|
|
|
if len(start_positions.size()) > 1: |
|
start_positions = start_positions.squeeze(-1) |
|
if len(end_positions.size()) > 1: |
|
end_positions = end_positions.squeeze(-1) |
|
|
|
ignored_index = start_logits.size(1) |
|
start_positions = start_positions.clamp(0, ignored_index) |
|
end_positions = end_positions.clamp(0, ignored_index) |
|
|
|
loss_fct = CrossEntropyLoss(ignore_index=ignored_index) |
|
start_loss = loss_fct(start_logits, start_positions) |
|
end_loss = loss_fct(end_logits, end_positions) |
|
total_loss = (start_loss + end_loss) / 2 |
|
|
|
if not return_dict: |
|
output = (start_logits, end_logits) + outputs[2:] |
|
return ((total_loss,) + output) if total_loss is not None else output |
|
|
|
return QuestionAnsweringModelOutput( |
|
loss=total_loss, |
|
start_logits=start_logits, |
|
end_logits=end_logits, |
|
hidden_states=outputs.hidden_states, |
|
attentions=outputs.attentions, |
|
) |
|
|
|
|