mdistilbertV2.1
- distilbert-base-multilingual-cased 모델에 moco-corpus-kowiki2022 말뭉치(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
from transformers import AutoTokenizer, AutoModel, DistilBertForMaskedLM
import torch
import torch.nn.functional as F
tokenizer = AutoTokenizer.from_pretrained('bongsoo/mdistilbertV2.1', do_lower_case=False)
model = DistilBertForMaskedLM.from_pretrained('bongsoo/mdistilbertV2.1')
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] : 프랑스 (47364)
*Input: 충무공 이순신은 [MASK]에 최고의 장수였다
*[MASK] : 임진왜란 (122835)
2. 임베딩 예시
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/mdistilbertV2.1')
model = AutoModel.from_pretrained('bongsoo/mdistilbertV2.1')
# 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
Sentence embeddings:
tensor([[-0.0166, 0.0129, 0.2805, ..., -0.1452, -0.0855, -0.4914],
[-0.0973, 0.0845, 0.2841, ..., 0.1996, -0.1497, -0.2990]])
*cosine_score:0.5162007808685303
Training
MLM(Masked Langeuage Model) 훈련
- 입력 모델 : distilbert-base-multilingual-cased
- 말뭉치 : 훈련 : bongsoo/moco-corpus-kowiki2022(7.6M) , 평가: bongsoo/bongevalsmall
- 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 : mdistilbertV2.1 (size: 613MB)
- 훈련시간 : 63h/1GPU (24GB/23.9 use)
- loss : 훈련loss: 2.203400, 평가loss: 2.972835, perplexity: 23.43(bong_eval:1,500)
- 훈련코드 여기 참조
perplexity 평가 코드는 여기 참조
Model Config
{
"_name_or_path": "../../data11/model/distilbert/mdistilbertV2.1-4",
"activation": "gelu",
"architectures": [
"DistilBertForMaskedLM"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"output_past": true,
"pad_token_id": 0,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"torch_dtype": "float32",
"transformers_version": "4.21.2",
"vocab_size": 152537
}
Citing & Authors
bongsoo
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.