---
license: apache-2.0
pipeline_tag: fill-mask
tags:
- fill-mask
- transformers
- en
- ko
widget:
  - text: 대한민국의 수도는 [MASK] 입니다.
---
# mbertV2.0

- bert-base-multilingual-cased 모델에 [moco-corpus-kowiki2022 말뭉치](https://huggingface.co/datasets/bongsoo/moco-corpus-kowiki2022)(kowiki202206 + MOCOMSYS 추출 3.2M 문장)로  vocab 추가하여 학습 시킨 모델
- **vocab: 152,537개**(기존 bert 모델 vocab(119,548개)에 32,989개 vocab 추가)

## Usage (HuggingFace Transformers)

### 1. MASK 예시
```python
from transformers import AutoTokenizer, AutoModel, BertForMaskedLM
import torch
import torch.nn.functional as F

tokenizer = AutoTokenizer.from_pretrained('bongsoo/mbertV2.0', do_lower_case=False)
model = BertForMaskedLM.from_pretrained('bongsoo/mbertV2.0')

text = ['한국의 수도는 [MASK] 이다', '에펠탑은 [MASK]에 있다', '충무공 이순신은 [MASK]에 최고의 장수였다']
tokenized_input = tokenizer(text, max_length=128, truncation=True, padding='max_length', return_tensors='pt')

outputs = model(**tokenized_input)
logits = outputs.logits

mask_idx_list = []
for tokens in tokenized_input['input_ids'].tolist():
    token_str = [tokenizer.convert_ids_to_tokens(s) for s in tokens]
    
    # **위 token_str리스트에서 [MASK] 인덱스를 구함
    # => **해당 [MASK] 안덱스 값 mask_idx 에서는 아래 출력하는데 사용됨
    mask_idx = token_str.index('[MASK]')
    mask_idx_list.append(mask_idx)
    
for idx, mask_idx in enumerate(mask_idx_list):
    
    logits_pred=torch.argmax(F.softmax(logits[idx]), dim=1)
    mask_logits_idx = int(logits_pred[mask_idx])
    # [MASK]에 해당하는 token 구함
    mask_logits_token = tokenizer.convert_ids_to_tokens(mask_logits_idx)
    # 결과 출력 
    print('\n')
    print('*Input: {}'.format(text[idx]))
    print('*[MASK] : {} ({})'.format(mask_logits_token, mask_logits_idx))
```
- 결과
```
*Input: 한국의 수도는 [MASK] 이다
*[MASK] : 서울 (48253)


*Input: 에펠탑은 [MASK]에 있다
*[MASK] : 런던 (120350)


*Input: 충무공 이순신은 [MASK]에 최고의 장수였다
*[MASK] : 조선 (59906)
```
### 2. 임베딩 예시
- 평균 폴링(mean_pooling) 방식 사용. ([cls 폴링](https://huggingface.co/sentence-transformers/bert-base-nli-cls-token), [max 폴링](https://huggingface.co/sentence-transformers/bert-base-nli-max-tokens))

```python
from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('bongsoo/mbertV2.0')
model = AutoModel.from_pretrained('bongsoo/mbertV2.0')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

# sklearn 을 이용하여 cosine_scores를 구함
# => 입력값 embeddings 은 (1,768) 처럼 2D 여야 함.
from sklearn.metrics.pairwise import paired_cosine_distances, paired_euclidean_distances, paired_manhattan_distances
cosine_scores = 1 - (paired_cosine_distances(sentence_embeddings[0].reshape(1,-1), sentence_embeddings[1].reshape(1,-1)))

print(f'*cosine_score:{cosine_scores[0]}')
```
- 결과
```
*cosine_score:0.5596463680267334
```
## Training

**MLM(Masked Langeuage Model) 훈련**
- 입력 모델 : bert-base-multilingual-cased(vocab(119,548개))
- 말뭉치 : 훈련 : bongsoo/moco-corpus-kowiki2022(7.6M) , 평가: bongsoo/bongevalsmall(200)
- HyperParameter : **LearningRate : 5e-5, epochs: 8, batchsize: 32, max_token_len : 128**
- vocab : **152,537개** (기존 119,548 에 32,989 신규 vocab 추가)
- 출력 모델 : mbertV2.0 (size: 813MB)
- 훈련시간 : 90h/1GPU (24GB/19.6GB use)
- loss : **훈련loss: 2.258400, 평가loss: 3.102096, perplexity: 19.78158**([bongsoo/bongeval](https://huggingface.co/datasets/bongsoo/bongeval):1,500개)
- 훈련코드 [여기](https://github.com/kobongsoo/BERT/blob/master/bert/bert-MLM-Trainer-V1.2.ipynb) 참조
<br>perplexity 평가 코드는 [여기](https://github.com/kobongsoo/BERT/blob/master/bert/bert-perplexity-eval-V1.2.ipynb) 참조

## Model Config
```
{
  "_name_or_path": "bert-base-multilingual-cased",
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "directionality": "bidi",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "pooler_fc_size": 768,
  "pooler_num_attention_heads": 12,
  "pooler_num_fc_layers": 3,
  "pooler_size_per_head": 128,
  "pooler_type": "first_token_transform",
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.21.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 152537
}
```
## Citing & Authors

bongsoo