gte-micro

This is a distill of gte-small.

Intended purpose

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

Usage (same as gte-small)

Use in semantic-autocomplete OR in code

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

def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]

input_texts = [
    "what is the capital of China?",
    "how to implement quick sort in python?",
    "Beijing",
    "sorting algorithms"
]

tokenizer = AutoTokenizer.from_pretrained("Mihaiii/gte-micro")
model = AutoModel.from_pretrained("Mihaiii/gte-micro")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Use with sentence-transformers:

from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim

sentences = ['That is a happy person', 'That is a very happy person']

model = SentenceTransformer('Mihaiii/gte-micro')
embeddings = model.encode(sentences)
print(cos_sim(embeddings[0], embeddings[1]))

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.