s-xlmr-bn

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.

Model Details

• Model name: s-xlmr-bn
• Model version: 1.0
• Architecture: Sentence Transformer
• Language: Multilingual ( fine-tuned for Bengali Language)
• Base Models:
  • paraphrase-distilroberta-base-v2 [Teacher Model]
  • xlm-roberta-large [Student Model]

Training

The model was fine-tuned using Multilingual Knowledge Distillation method. We took paraphrase-distilroberta-base-v2 as the teacher model and xlm-roberta-large as the student model.

Intended Use:

• Primary Use Case: Semantic similarity, clustering, and semantic searches
• Potential Use Cases: Document retrieval, information retrieval, recommendation systems, chatbot systems , FAQ system

Usage

Using 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 = ["I sing in bengali", "আমি বাংলায় গান গাই"]

model = SentenceTransformer('afschowdhury/s-xlmr-bn')
embeddings = model.encode(sentences)
print(embeddings)

Using 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.

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 = ["I sing in bengali", "আমি বাংলায় গান গাই"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('afschowdhury/s-xlmr-bn')
model = AutoModel.from_pretrained('afschowdhury/s-xlmr-bn')

# 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)

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, '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})
)

Point of Contact

Asif Faisal Chowdhury
E-mail: afschowdhury@gmail.com | Linked-in: afschowdhury