File size: 4,020 Bytes
c8ef0a6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
import sentencepiece as spm
import re
# from datasets import load_dataset, DatasetDict, Dataset
# import random
# # Load code datasets
# code_dataset_go = load_dataset('code_x_glue_ct_code_to_text', 'go', split='train', cache_dir='/sml2/atul/CENTRAL_CACHE')['code'][:400000]
# code_dataset_java = load_dataset('code_x_glue_ct_code_to_text', 'java', split='train', cache_dir='/sml2/atul/CENTRAL_CACHE')['code'][:400000]
# code_dataset_javascript = load_dataset('code_x_glue_ct_code_to_text', 'javascript', split='train', cache_dir='/sml2/atul/CENTRAL_CACHE')['code'][:400000]
# code_dataset_php = load_dataset('code_x_glue_ct_code_to_text', 'php', split='train', cache_dir='/sml2/atul/CENTRAL_CACHE')['code'][:400000]
# code_dataset_python = load_dataset('code_x_glue_ct_code_to_text', 'python', split='train', cache_dir='/sml2/atul/CENTRAL_CACHE')['code'][:400000]
# code_dataset_ruby = load_dataset('code_x_glue_ct_code_to_text', 'ruby', split='train', cache_dir='/sml2/atul/CENTRAL_CACHE')['code'][:400000]
# # Load text datasets
# indic_datasets_hi = load_dataset('ai4bharat/sangraha', data_dir="verified/hin", cache_dir='/sml2/atul/CENTRAL_CACHE')['train']['text']
# indic_datasets_bn = load_dataset('ai4bharat/sangraha', data_dir="verified/ben", cache_dir='/sml2/atul/CENTRAL_CACHE')['train']['text']
# wikipedia_en = load_dataset("wikipedia", "20220301.en", cache_dir='/sml2/atul/CENTRAL_CACHE')['train']['text']
# # Randomly sample a subset of text data
# num_docs = 500000
# hi_sampled = random.sample(indic_datasets_hi, num_docs)
# bn_sampled = random.sample(indic_datasets_bn, num_docs)
# en_sampled = random.sample(wikipedia_en, num_docs)
# # Combine sampled text datasets with code datasets
# combined_train_set = en_sampled + hi_sampled + bn_sampled
# combined_train_set_code = code_dataset_go + code_dataset_java + code_dataset_javascript + code_dataset_php + code_dataset_python + code_dataset_ruby
# # Write the combined data to the output file
# with open('traintext1.txt', 'w') as f:
# for text in combined_train_set:
# lines = text.split("\n")
# for l in lines:
# if l:
# f.write(l.strip() + '\n')
# for code in combined_train_set_code:
# f.write(code + '\n')
spm.SentencePieceTrainer.Train(
input='traintext1.txt',
model_prefix='50kspm_tokenizer_code',
vocab_size=50304,
pad_id=0,
unk_id=1,
bos_id=2,
eos_id=3,
pad_piece='<pad>',
unk_piece='<unk>',
bos_piece='<bos>',
eos_piece='<eos>',
model_type='bpe',
num_threads=256,
add_dummy_prefix=False,
byte_fallback=True,
character_coverage=0.9999,
remove_extra_whitespaces=False,
allow_whitespace_only_pieces=True,
split_digits=True,
user_defined_symbols='\n,\r,<pad>,<eos>,<bos>,<mask>,<unused0>,<unused1>,<unused2>,<unused3>,<unused4>,<unused5>,<unused6>,<unused7>,<unused8>,<unused9>,<unused10>,<unused11>,<unused12>,<unused13>,<unused14>,<unused15>,<unused16>,<unused17>,<unused18>,<unused19>,<unused20>,<unused21>,<unused22>,<unused23>,<unused24>,<unused25>,<unused26>,<unused27>,<unused28>,<unused29>,<unused30>,<unused31>,<unused32>,<unused33>,<unused34>,<unused35>,<unused36>,<unused37>,<unused38>,<unused39>,<unused40>,<unused41>,<unused42>,<unused43>,<unused44>,<unused45>,<unused46>,<unused47>,<unused48>,<unused49>,<unused50>,<unused51>,<unused52>,<unused53>,<unused54>,<unused55>,<unused56>,<unused57>,<unused58>,<unused59>,<unused60>,<unused61>,<unused62>,<unused63>,<unused64>,<unused65>,<unused66>,<unused67>,<unused68>,<unused69>,<unused70>,<unused71>,<unused72>,<unused73>,<unused74>,<unused75>,<unused76>,<unused77>,<unused78>,<unused79>,<unused80>,<unused81>,<unused82>,<unused83>,<unused84>,<unused85>,<unused86>,<unused87>,<unused88>,<unused89>,<unused90>,<unused91>,<unused92>,<unused93>,<unused94>,<unused95>,<unused96>,<unused97>,<unused98>,<start_of_turn>,<end_of_turn>,〈|javascript|〉,〈|python|〉,〈|sql|〉,〈|shell|〉,〈|c|〉,〈|cpp|〉,〈|java|〉,〈|go|〉',
)
|