chore: update from 07ce15d58b77559fce77ea89e92d398f28663bd9

configuration_bert.py

@@ -24,54 +24,10 @@ from transformers.utils import logging
 
 logger = logging.get_logger(__name__)
 
-BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/config.json",
-    "bert-large-uncased": "https://huggingface.co/bert-large-uncased/resolve/main/config.json",
-    "bert-base-cased": "https://huggingface.co/bert-base-cased/resolve/main/config.json",
-    "bert-large-cased": "https://huggingface.co/bert-large-cased/resolve/main/config.json",
-    "bert-base-multilingual-uncased": "https://huggingface.co/bert-base-multilingual-uncased/resolve/main/config.json",
-    "bert-base-multilingual-cased": "https://huggingface.co/bert-base-multilingual-cased/resolve/main/config.json",
-    "bert-base-chinese": "https://huggingface.co/bert-base-chinese/resolve/main/config.json",
-    "bert-base-german-cased": "https://huggingface.co/bert-base-german-cased/resolve/main/config.json",
-    "bert-large-uncased-whole-word-masking": (
-        "https://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/config.json"
-    ),
-    "bert-large-cased-whole-word-masking": (
-        "https://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/config.json"
-    ),
-    "bert-large-uncased-whole-word-masking-finetuned-squad": (
-        "https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/config.json"
-    ),
-    "bert-large-cased-whole-word-masking-finetuned-squad": (
-        "https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/config.json"
-    ),
-    "bert-base-cased-finetuned-mrpc": "https://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/config.json",
-    "bert-base-german-dbmdz-cased": "https://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/config.json",
-    "bert-base-german-dbmdz-uncased": "https://huggingface.co/bert-base-german-dbmdz-uncased/resolve/main/config.json",
-    "cl-tohoku/bert-base-japanese": "https://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/config.json",
-    "cl-tohoku/bert-base-japanese-whole-word-masking": (
-        "https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/config.json"
-    ),
-    "cl-tohoku/bert-base-japanese-char": (
-        "https://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/config.json"
-    ),
-    "cl-tohoku/bert-base-japanese-char-whole-word-masking": (
-        "https://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/config.json"
-    ),
-    "TurkuNLP/bert-base-finnish-cased-v1": (
-        "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/config.json"
-    ),
-    "TurkuNLP/bert-base-finnish-uncased-v1": (
-        "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/config.json"
-    ),
-    "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/config.json",
-    # See all BERT models at https://huggingface.co/models?filter=bert
-}
-
 
 class JinaBertConfig(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of a [`BertModel`] or a [`TFBertModel`]. It is used to
+    This is the configuration class to store the configuration of a [`JinaBertModel`]. It is used to
     instantiate a BERT model according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the BERT
     [bert-base-uncased](https://huggingface.co/bert-base-uncased) architecture.
@@ -149,6 +105,9 @@ class JinaBertConfig(PretrainedConfig):
 
     >>> # Accessing the model configuration
     >>> configuration = model.config
+
+    >>> # Encode text inputs
+    >>> embeddings = model.encode(text_inputs)
     ```"""
     model_type = "bert"
 

flash_attn_triton.py

@@ -1156,5 +1156,4 @@ class FlashAttnFunc(torch.autograd.Function):
             )
         return dq, dk, dv, None, None, None
 
-
 flash_attn_func = FlashAttnFunc.apply

modeling_bert.py

@@ -101,33 +101,6 @@ _SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
 _SEQ_CLASS_EXPECTED_LOSS = 0.01
 
 
-BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [
-    "bert-base-uncased",
-    "bert-large-uncased",
-    "bert-base-cased",
-    "bert-large-cased",
-    "bert-base-multilingual-uncased",
-    "bert-base-multilingual-cased",
-    "bert-base-chinese",
-    "bert-base-german-cased",
-    "bert-large-uncased-whole-word-masking",
-    "bert-large-cased-whole-word-masking",
-    "bert-large-uncased-whole-word-masking-finetuned-squad",
-    "bert-large-cased-whole-word-masking-finetuned-squad",
-    "bert-base-cased-finetuned-mrpc",
-    "bert-base-german-dbmdz-cased",
-    "bert-base-german-dbmdz-uncased",
-    "cl-tohoku/bert-base-japanese",
-    "cl-tohoku/bert-base-japanese-whole-word-masking",
-    "cl-tohoku/bert-base-japanese-char",
-    "cl-tohoku/bert-base-japanese-char-whole-word-masking",
-    "TurkuNLP/bert-base-finnish-cased-v1",
-    "TurkuNLP/bert-base-finnish-uncased-v1",
-    "wietsedv/bert-base-dutch-cased",
-    # See all BERT models at https://huggingface.co/models?filter=bert
-]
-
-
 def load_tf_weights_in_bert(model, config, tf_checkpoint_path):
     """Load tf checkpoints in a pytorch model."""
     try:
@@ -2396,3 +2369,4 @@ class JinaBertForQuestionAnswering(JinaBertPreTrainedModel):
             hidden_states=outputs.hidden_states,
             attentions=outputs.attentions,
         )
+