paraphrase-MiniLM-L12-tagalog-v2

st1992/paraphrase-MiniLM-L12-tagalog-v2

paraphrase-MiniLM-L12-v2 finetuned on Tagalog language: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers) : same as other sentence-transformer models

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('st1992/paraphrase-MiniLM-L12-tagalog-v2')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

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 = ['hindi po', 'tulog na']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('st1992/paraphrase-MiniLM-L12-tagalog-v2')
model = AutoModel.from_pretrained('st1992/paraphrase-MiniLM-L12-tagalog-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, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)