You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
초보자가 'KiwiTokenizer' 한번 사용해볼려고 제시한 예제대로 해봤는데 다음과 같은 에러가 나네요. 그리고 KiwiTokenizer가 들어간 kiwi-farm에서 제시한 예제 코드나 그 외 다른 코드라던지 전부 'KiwiTokenizer' 때문에 에러가 발생하던데요?(혹시 잘못 알고 있다면 지적 바랍니다)
import kiwipiepy
from kiwipiepy import KiwiTokenizer
ImportError Traceback (most recent call last)
Cell In[3], line 2
1 import kiwipiepy
----> 2 from kiwipiepy import KiwiTokenizer
ImportError: cannot import name 'KiwiTokenizer' from 'kiwipiepy' (D:\projects\kiwi\kiwipiepy_init_.py)
from datasets import load_dataset
import os
from kiwipiepy import Kiwi
from kiwipiepy.utils import Stopwords
data_dir = './data'
dataset = load_dataset('nsmc')
os.makedirs(data_dir, exist_ok=True)
for split_key in dataset.keys():
doc_path = f"{data_dir}/{split_key}.txt"
with open(doc_path, 'w', encoding='utf-8') as f:
for doc in dataset[split_key]['document']:
f.write(doc + '\n')
kiwi = Kiwi()
stopwords = Stopwords()
ImportError Traceback (most recent call last)
Cell In[3], line 3
1 from datasets import load_dataset
2 import os
----> 3 from kiwipiepy import Kiwi
4 from kiwipiepy.utils import Stopwords
6 data_dir = './data'
File D:\projects\kiwi\kiwipiepy_init_.py:7
5 from kiwipiepy._version import version
6 from kiwipiepy._wrap import Kiwi, Sentence, TypoTransformer, TypoDefinition, HSDataset, MorphemeSet, PretokenizedToken
----> 7 import kiwipiepy.sw_tokenizer as sw_tokenizer
8 import kiwipiepy.utils as utils
9 from kiwipiepy.const import Match
File D:\projects\kiwi\kiwipiepy\sw_tokenizer.py:15
11 import warnings
13 import tqdm
---> 15 from _kiwipiepy import Sw_Tokenizer
17 from kiwipiepy import Kiwi, Token
19 @DataClass
20 class SwTokenizerConfig:
ImportError: cannot import name 'Sw_Tokenizer' from '_kiwipiepy' (D:\anaconda3\Lib\site-packages_kiwipiepy.cp311-win_amd64.pyd)
<= 이렇게 하는 코드는 원래 안되는 것인가요?
from transformers import AutoModelForMaskedLM
from kiwipiepy.sw_tokenizer import SwTokenizer
import kiwipiepy.transformers_addon
from kiwipiepy.sw_tokenizer import KiwiTokenizer
tokenizer = KiwiTokenizer.from_pretrained('kiwi-farm/roberta-base-32k')
#tokenizer = SwTokenizer.KiwiTokenizer("kiwi-farm/roberta-base-32k")
model = AutoModelForMaskedLM.from_pretrained('kiwi-farm/roberta-base-32k')
model.config.is_decoder = True # Set the model as a decoder
ImportError Traceback (most recent call last)
Cell In[1], line 2
1 from transformers import AutoModelForMaskedLM
----> 2 from kiwipiepy.sw_tokenizer import SwTokenizer
3 import kiwipiepy.transformers_addon
4 from kiwipiepy.sw_tokenizer import KiwiTokenizer
File D:\projects\kiwi\kiwipiepy_init_.py:7
5 from kiwipiepy._version import version
6 from kiwipiepy._wrap import Kiwi, Sentence, TypoTransformer, TypoDefinition, HSDataset, MorphemeSet, PretokenizedToken
----> 7 import kiwipiepy.sw_tokenizer as sw_tokenizer
8 import kiwipiepy.utils as utils
9 from kiwipiepy.const import Match
File D:\projects\kiwi\kiwipiepy\sw_tokenizer.py:15
11 import warnings
13 import tqdm
---> 15 from _kiwipiepy import Sw_Tokenizer
17 from kiwipiepy import Kiwi, Token
19 @DataClass
20 class SwTokenizerConfig:
ImportError: cannot import name 'Sw_Tokenizer' from '_kiwipiepy' (D:\anaconda3\Lib\site-packages_kiwipiepy.cp311-win_amd64.pyd)
The text was updated successfully, but these errors were encountered:
초보자가 'KiwiTokenizer' 한번 사용해볼려고 제시한 예제대로 해봤는데 다음과 같은 에러가 나네요. 그리고 KiwiTokenizer가 들어간 kiwi-farm에서 제시한 예제 코드나 그 외 다른 코드라던지 전부 'KiwiTokenizer' 때문에 에러가 발생하던데요?(혹시 잘못 알고 있다면 지적 바랍니다)
import kiwipiepy
from kiwipiepy import KiwiTokenizer
ImportError Traceback (most recent call last)
Cell In[3], line 2
1 import kiwipiepy
----> 2 from kiwipiepy import KiwiTokenizer
ImportError: cannot import name 'KiwiTokenizer' from 'kiwipiepy' (D:\projects\kiwi\kiwipiepy_init_.py)
from datasets import load_dataset
import os
from kiwipiepy import Kiwi
from kiwipiepy.utils import Stopwords
data_dir = './data'
dataset = load_dataset('nsmc')
os.makedirs(data_dir, exist_ok=True)
for split_key in dataset.keys():
doc_path = f"{data_dir}/{split_key}.txt"
with open(doc_path, 'w', encoding='utf-8') as f:
for doc in dataset[split_key]['document']:
f.write(doc + '\n')
kiwi = Kiwi()
stopwords = Stopwords()
ImportError Traceback (most recent call last)
Cell In[3], line 3
1 from datasets import load_dataset
2 import os
----> 3 from kiwipiepy import Kiwi
4 from kiwipiepy.utils import Stopwords
6 data_dir = './data'
File D:\projects\kiwi\kiwipiepy_init_.py:7
5 from kiwipiepy._version import version
6 from kiwipiepy._wrap import Kiwi, Sentence, TypoTransformer, TypoDefinition, HSDataset, MorphemeSet, PretokenizedToken
----> 7 import kiwipiepy.sw_tokenizer as sw_tokenizer
8 import kiwipiepy.utils as utils
9 from kiwipiepy.const import Match
File D:\projects\kiwi\kiwipiepy\sw_tokenizer.py:15
11 import warnings
13 import tqdm
---> 15 from _kiwipiepy import Sw_Tokenizer
17 from kiwipiepy import Kiwi, Token
19 @DataClass
20 class SwTokenizerConfig:
ImportError: cannot import name 'Sw_Tokenizer' from '_kiwipiepy' (D:\anaconda3\Lib\site-packages_kiwipiepy.cp311-win_amd64.pyd)
from transformers import AutoModelForMaskedLM
from kiwipiepy.sw_tokenizer import SwTokenizer
import kiwipiepy.transformers_addon
from kiwipiepy.sw_tokenizer import KiwiTokenizer
tokenizer = KiwiTokenizer.from_pretrained('kiwi-farm/roberta-base-32k')
#tokenizer = SwTokenizer.KiwiTokenizer("kiwi-farm/roberta-base-32k")
model = AutoModelForMaskedLM.from_pretrained('kiwi-farm/roberta-base-32k')
model.config.is_decoder = True # Set the model as a decoder
prompt = "Gim"
input_ids = tokenizer.encode(prompt, return_tensors="pt")
Generate text using top-k sampling
gen_ids = model.generate(
input_ids,
max_length=50,
do_sample=True, # Enable sampling
top_k=50 # Top-k sampling
)
generated_text = tokenizer.decode(gen_ids[0], skip_special_tokens=True)
print(generated_text)
ImportError Traceback (most recent call last)
Cell In[1], line 2
1 from transformers import AutoModelForMaskedLM
----> 2 from kiwipiepy.sw_tokenizer import SwTokenizer
3 import kiwipiepy.transformers_addon
4 from kiwipiepy.sw_tokenizer import KiwiTokenizer
File D:\projects\kiwi\kiwipiepy_init_.py:7
5 from kiwipiepy._version import version
6 from kiwipiepy._wrap import Kiwi, Sentence, TypoTransformer, TypoDefinition, HSDataset, MorphemeSet, PretokenizedToken
----> 7 import kiwipiepy.sw_tokenizer as sw_tokenizer
8 import kiwipiepy.utils as utils
9 from kiwipiepy.const import Match
File D:\projects\kiwi\kiwipiepy\sw_tokenizer.py:15
11 import warnings
13 import tqdm
---> 15 from _kiwipiepy import Sw_Tokenizer
17 from kiwipiepy import Kiwi, Token
19 @DataClass
20 class SwTokenizerConfig:
ImportError: cannot import name 'Sw_Tokenizer' from '_kiwipiepy' (D:\anaconda3\Lib\site-packages_kiwipiepy.cp311-win_amd64.pyd)
The text was updated successfully, but these errors were encountered: