o
    iq                     @   s  d Z ddlmZ ddlmZ ddlmZ ddlm	Z
 e
 Ze dZeee  eede  ejdkrd	e_d
e_d	ejd _dejd _d	ejd _dejd _de_de_de_de_de_de_de_de_de_de_de_de_de_de_de_de_d	S d	S )zGenerated protocol buffer code.    )builder)
descriptor)descriptor_pool)symbol_databases	  
sentencepiece_model.protosentencepiece"
TrainerSpec
input (	
input_format (	
model_prefix (	A

model_type (2$.sentencepiece.TrainerSpec.ModelType:UNIGRAM

vocab_size (:8000
accept_language (	 
self_test_sample_size (:0*
enable_differential_privacy2 (:false+
 differential_privacy_noise_level3 (:02
'differential_privacy_clipping_threshold4 (:0"
character_coverage
 (:0.9995
input_sentence_size (:0$
shuffle_input_sentence (:true 
mining_sentence_size (B"
training_sentence_size (B(
seed_sentencepiece_size (:1000000
shrinking_factor (:0.75!
max_sentence_length (:4192
num_threads (:16
num_sub_iterations (:2$
max_sentencepiece_length (:16%
split_by_unicode_script (:true
split_by_number (:true!
split_by_whitespace (:true)
treat_whitespace_as_suffix (:false+
allow_whitespace_only_pieces (:false
split_digits (:false#
pretokenization_delimiter5 (	: 
control_symbols (	
user_defined_symbols (	
required_chars$ (	
byte_fallback# (:false+
vocabulary_output_piece_score  (:true
hard_vocab_limit! (:true
use_all_vocab" (:false
unk_id( (:0
bos_id) (:1
eos_id* (:2
pad_id+ (:-1
	unk_piece- (	:<unk>
	bos_piece. (	:<s>
	eos_piece/ (	:</s>
	pad_piece0 (	:<pad>
unk_surface, (	: ⁇ +
train_extremely_large_corpus1 (:false"5
	ModelType
UNIGRAM
BPE
WORD
CHAR*	"
NormalizerSpec
name (	
precompiled_charsmap (
add_dummy_prefix (:true&
remove_extra_whitespaces (:true 
escape_whitespaces (:true
normalization_rule_tsv (	*	"y
SelfTestData3
samples (2".sentencepiece.SelfTestData.Sample)
Sample
input (	
expected (	*	"

ModelProto7
pieces (2'.sentencepiece.ModelProto.SentencePiece0
trainer_spec (2.sentencepiece.TrainerSpec6
normalizer_spec (2.sentencepiece.NormalizerSpec3
self_test_data (2.sentencepiece.SelfTestData8
denormalizer_spec (2.sentencepiece.NormalizerSpec
SentencePiece
piece (	
score (B
type (2,.sentencepiece.ModelProto.SentencePiece.Type:NORMAL"T
Type

NORMAL
UNKNOWN
CONTROL
USER_DEFINED
BYTE

UNUSED*	*	BHsentencepiece_model_pb2FNs   Hmining_sentence_sizes   training_sentence_size-   i-  i  i"  i0  i  i  i|  iH  iq  i  i}	  i  ir	  i	  ig	  ) __doc__google.protobuf.internalr   _buildergoogle.protobufr   _descriptorr   _descriptor_poolr   _symbol_databaseDefault_sym_dbAddSerializedFile
DESCRIPTORBuildMessageAndEnumDescriptorsglobalsBuildTopDescriptorsAndMessages_USE_C_DESCRIPTORS_options_serialized_options_TRAINERSPECfields_by_name_serialized_start_serialized_end_TRAINERSPEC_MODELTYPE_NORMALIZERSPEC_SELFTESTDATA_SELFTESTDATA_SAMPLE_MODELPROTO_MODELPROTO_SENTENCEPIECE_MODELPROTO_SENTENCEPIECE_TYPE r&   r&   g/sda-disk/www/egybert/egybert_env/lib/python3.10/site-packages/sentencepiece/sentencepiece_model_pb2.py<module>   sB   

