Mihaiii / gte-micro-v4

gte-micro-v4

This is a distill of gte-tiny .

Intended purpose

This model is designed for use in semantic-autocomplete ( click here for demo ).

Usage (Sentence-Transformers) (same as gte-tiny )

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 = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('Mihaiii/gte-micro-v4')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers) (same as gte-tiny )

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 = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('Mihaiii/gte-micro-v4')
model = AutoModel.from_pretrained('Mihaiii/gte-micro-v4')

# 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)

Limitation (same as gte-small )

This model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens.