Chula Course Paraphrase Multilingual Mpnet Base V2

🚀 new5558/chula-course-paraphrase-multilingual-mpnet-base-v2

This is a sentence-transformers model that maps sentences and paragraphs to a 768-dimensional dense vector space, useful for tasks like clustering or semantic search.

🚀 Quick Start

This model can be used in two ways, either with sentence-transformers or directly with HuggingFace Transformers.

📦 Installation

If you want to use the sentence-transformers approach, you need to install the library first:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage with Sentence-Transformers

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

model = SentenceTransformer('new5558/chula-course-paraphrase-multilingual-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage with HuggingFace Transformers

Without sentence-transformers, you can use the model by passing your input through the transformer model and then applying the right pooling operation on top of the contextualized word embeddings.

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('new5558/chula-course-paraphrase-multilingual-mpnet-base-v2')
model = AutoModel.from_pretrained('new5558/chula-course-paraphrase-multilingual-mpnet-base-v2')

# 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)

📚 Documentation

Evaluation Results

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

Training

The model was trained with the following parameters:

DataLoader: torch.utils.data.dataloader.DataLoader of length 49314 with parameters:

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

Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

Parameters of the fit()-Method:

{
    "epochs": 1,
    "evaluation_steps": 2000,
    "evaluator": "__main__.EmbeddingSimilarityOptimizedEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 10000,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (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