ALJIACHI / momen-text-embed-v1

momen-text-embed-v1

momen-text-embed-v1 maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. it surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks in arabic language.

Performance Benchmarks

Soon

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 = ['هذه جملة لغرض التجربة', 'جملة باللغة العربية ليتم تحويلها']

model = SentenceTransformer('ALJIACHI/momen-text-embed-v1')
embeddings = model.encode(sentences)
print(embeddings)

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.

from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F

#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 = ['هذه جملة لغرض التجربة', 'جملة باللغة العربية ليتم تحويلها']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('ALJIACHI/momen-text-embed-v1')
model = AutoModel.from_pretrained('ALJIACHI/momen-text-embed-v1')

# 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
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)

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