This is a distill of gte-tiny.
This model is designed for use in semantic-autocomplete (click here for demo).
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformersThen 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-v2')
embeddings = model.encode(sentences)
print(embeddings)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 openmind import AutoModel, AutoTokenizer , is_torch_npu_available
from openmind_hub import snapshot_download
import torch
import argparse
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--model_name_or_path",
type=str,
help="Path to model",
default="jeffding/gte-micro-v2-openmind",
)
args = parser.parse_args()
return args
#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)
def main():
args = parse_args()
model_path = args.model_name_or_path
if is_torch_npu_available():
device = "npu:0"
else:
device = "cpu"
# 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(model_path)
model = AutoModel.from_pretrained(model_path)
# 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)
if __name__ == "__main__":
print(sentence_embeddings)
main()This model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens.