Roberta Zwnj Wnli Mean Tokens

🚀 Sentence Embeddings with roberta-zwnj-wnli-mean-tokens

This project provides sentence embeddings using the roberta-zwnj-wnli-mean-tokens model, enabling feature extraction and sentence similarity analysis.

🚀 Quick Start

This model simplifies the process of generating sentence embeddings. You can use it in two ways, either with the sentence-transformers library or directly with HuggingFace Transformers.

📦 Installation

If you choose to use the sentence-transformers library, you need to install it first:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage (Sentence-Transformers)

When you have sentence-transformers installed, using this model is straightforward:

from sentence_transformers import SentenceTransformer

sentences = [
    'اولین حکمران شهر بابل کی بود؟',
    'در فصل زمستان چه اتفاقی افتاد؟',
    'میراث کوروش'
]
model = SentenceTransformer('m3hrdadfi/roberta-zwnj-wnli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model as follows. First, pass your input through the transformer model, then apply the appropriate pooling operation on top of the contextualized word embeddings:

from transformers import AutoTokenizer, AutoModel
import torch

# Max Pooling - Take the max value over time for every dimension. 
def max_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()
    token_embeddings[input_mask_expanded == 0] = -1e9  # Set padding tokens to large negative value
    return torch.mean(token_embeddings, 1)[0]

# Sentences we want sentence embeddings for
sentences = [
    'اولین حکمران شهر بابل کی بود؟',
    'در فصل زمستان چه اتفاقی افتاد؟',
    'میراث کوروش'
]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('m3hrdadfi/roberta-zwnj-wnli-mean-tokens')
model = AutoModel.from_pretrained('m3hrdadfi/roberta-zwnj-wnli-mean-tokens')

# 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, max pooling.
sentence_embeddings = max_pooling(model_output, encoded_input['attention_mask'])

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

📚 Documentation

Questions?

If you have any questions, please post a Github issue from HERE.