Bombek1/all-mpnet-base-v2-litert

import numpy as np
from ai_edge_litert.interpreter import Interpreter
from transformers import AutoTokenizer

# Load model and tokenizer
interpreter = Interpreter(model_path="sentence-transformers_all-mpnet-base-v2.tflite")
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-mpnet-base-v2")

def get_embedding(text: str) -> np.ndarray:
    """Get sentence embedding for input text."""
    encoded = tokenizer(
        text,
        padding="max_length",
        max_length=128,
        truncation=True,
        return_tensors="np"
    )

    interpreter.set_tensor(input_details[0]["index"], encoded["input_ids"].astype(np.int64))
    interpreter.set_tensor(input_details[1]["index"], encoded["attention_mask"].astype(np.int64))
    interpreter.invoke()

    return interpreter.get_tensor(output_details[0]["index"])[0]

# Example
embedding = get_embedding("Hello, world!")
print(f"Embedding shape: {embedding.shape}")  # (768,)

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "EMNLP 2019",
    year = "2019",
    url = "https://arxiv.org/abs/1908.10084",
}