Getting error while loading saved DistilBert embeddings model.

[Saksham2805]

I am trying to convert the Hugging face embeddings to Spark NLP but it is giving this error.

Py4JJavaError: An error occurred while calling z:com.johnsnowlabs.nlp.embeddings.DistilBertEmbeddings.loadSavedModel.
: org.tensorflow.exceptions.TFInvalidArgumentException: indices[0,11] = 28937 is not in [0, 25000)
	 [[{{function_node __inference_serving_fn_7666}}{{node tf_distil_bert_model_1/distilbert/embeddings/Gather}}]]
	at org.tensorflow.internal.c_api.AbstractTF_Status.throwExceptionIfNotOK(AbstractTF_Status.java:87)
	at org.tensorflow.Session.run(Session.java:850)
	at org.tensorflow.Session.access$300(Session.java:82)
	at org.tensorflow.Session$Runner.runHelper(Session.java:552)
	at org.tensorflow.Session$Runner.runNoInit(Session.java:499)
	at org.tensorflow.Session$Runner.run(Session.java:495)
	at com.johnsnowlabs.ml.ai.DistilBert.tag(DistilBert.scala:168)

I used the following code block

from sparknlp.annotator import *

distil_bert = DistilBertEmbeddings.loadSavedModel(
     '/content/drive/MyDrive/Portuguese/new_embed/{}/saved_model/1'.format(MODEL_NAME),
     spark
 )\
 .setMaxSentenceLength(512)\
 .setInputCols(["sentence",'token'])\
 .setOutputCol("embeddings")\
 .setCaseSensitive(False)\
 .setDimension(768)\
 .setStorageRef('distilbert_base_uncased') 

I am using the Spark version = 3.1.2 and SparkNLP version = 5.2.3 The model i am downloading is "Geotrend/distilbert-base-pt-cased"

I have also tried to load these embeddings from John snow labs models hub , but the error is just the same in that case also. Please help if anyone else also faced this error.