moco-sentencedistilbertV2.0

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

<!--- Describe your model here -->

• 이 모델은 mdistilbertV1.1 모델에 moco-corpus 말뭉치(MOCOMSYS 추출 3.2M 문장)로 <br>sentencebert로 만든 후,추가적으로 STS Tearch-student 증류 학습 시켜 만든 모델 입니다.
• vocab: 164,314 개(기존 mdistilbertV1.1 vocab(146,444 개)에 17,870개 vocab 추가) <br> MLM 모델 : bongsoo/mdistilbertV2.0

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence_transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('bongsoo/moco-sentencedistilbertV2.0')
embeddings = model.encode(sentences)
print(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(embeddings[0].reshape(1,-1), embeddings[1].reshape(1,-1)))

print(f'*cosine_score:{cosine_scores[0]}')

출력(Outputs)

[[ 9.7172342e-02 -3.3226651e-01 -7.7130608e-05 ...  1.3900512e-02 2.1072578e-01 -1.5386048e-01]
 [ 2.3313640e-02 -8.4675789e-02 -3.7715461e-06 ...  2.4005771e-02 -1.6602692e-01 -1.2729791e-01]]
*cosine_score:0.3383665680885315

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

• 평균 폴링(mean_pooling) 방식 사용. (cls 폴링, max 폴링)

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/moco-sentencedistilbertV2.0')
model = AutoModel.from_pretrained('bongsoo/moco-sentencedistilbertV2.0')

# 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]}')

출력(Outputs)

Sentence embeddings:
tensor([[ 9.7172e-02, -3.3227e-01, -7.7131e-05,  ...,  1.3901e-02, 2.1073e-01, -1.5386e-01],
        [ 2.3314e-02, -8.4676e-02, -3.7715e-06,  ...,  2.4006e-02, -1.6603e-01, -1.2730e-01]])
*cosine_score:0.3383665680885315

Evaluation Results

<!--- Describe how your model was evaluated -->

• 성능 측정을 위한 말뭉치는, 아래 한국어 (kor), 영어(en) 평가 말뭉치를 이용함 <br> 한국어 : korsts(1,379쌍문장) 와 klue-sts(519쌍문장) <br> 영어 : stsb_multi_mt(1,376쌍문장)
• 성능 지표는 cosin.spearman 측정하여 비교함.
• 평가 측정 코드는 여기 참조

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training(훈련 과정)

The model was trained with the parameters:

1. MLM 훈련

• 입력 모델 : bongsoo/mdistilbertV1.1(*kowiki20220620(4.4M) 말뭉치 훈련된 distilbert-base-multilingual-cased)
• 말뭉치 : nlp_corpus(3.2M) : MOCOMSYS 파일들 정제한 말뭉치
• HyperParameter : LearningRate : 5e-5, epochs: 8, batchsize: 32, max_token_len : 128
• 출력 모델 : mdistilbertV2.0
• 훈련시간 : 27h
• 훈련코드 여기 참조

2. STS 훈련

• distilbert를 sentencebert로 만듬.
• 입력 모델 : mdistilbertV2.0
• 말뭉치 : korsts + kluestsV1.1 + stsb_multi_mt + mteb/sickr-sts (총:33,093)
• HyperParameter : LearningRate : 2e-5, epochs: 200, batchsize: 32, max_token_len : 128
• 출력 모델 : sbert-mdistilbertV2.0
• 훈련시간 : 5h
• 훈련코드 여기 참조

3.증류(distilation) 훈련

• 학생 모델 : sbert-mdistilbertV2.0
• 교사 모델 : paraphrase-multilingual-mpnet-base-v2
• 말뭉치 : en_ko_train.tsv(한국어-영어 사회과학분야 병렬 말뭉치 : 1.1M)
• HyperParameter : LearningRate : 5e-5, epochs: 40, batchsize: 32, max_token_len : 128
• 출력 모델 : sbert-mdistilbertV2.0.2-distil
• 훈련시간 : 11h
• 훈련코드 여기 참조

4.STS 훈련 -sentencebert 모델을 sts 훈련시킴

• 입력 모델 : sbert-mdistilbertV2.0.2-distil
• 말뭉치 : korsts + kluestsV1.1 + stsb_multi_mt + mteb/sickr-sts (총:33,093)
• HyperParameter : LearningRate : 3e-5, epochs: 800, batchsize: 32, max_token_len : 128
• 출력 모델 : moco-sentencedistilbertV2.0
• 훈련시간 : 15h
• 훈련코드 여기 참조

<br>모델 제작 과정에 대한 자세한 내용은 여기를 참조 하세요.

DataLoader:

torch.utils.data.dataloader.DataLoader of length 1035 with parameters:

{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Config:

{
  "_name_or_path": "../../data11/model/sbert/sbert-mdistilbertV2.0.2-distil",
  "activation": "gelu",
  "architectures": [
    "DistilBertModel"
  ],
  "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": 164314
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

<!--- Describe where people can find more information --> bongsoo