Bombek1/multi-qa-mpnet-base-dot-v1-litert

multi-qa-mpnet-base-dot-v1 - LiteRT

This is a LiteRT (formerly TensorFlow Lite) conversion of sentence-transformers/multi-qa-mpnet-base-dot-v1 for efficient on-device inference.

Model Details

Property	Value
Original Model	sentence-transformers/multi-qa-mpnet-base-dot-v1
Format	LiteRT (.tflite)
File Size	416.0 MB
Task	Question Answering / Semantic Search
Max Sequence Length	512
Output Dimension	768
Pooling Mode	Mean Pooling

Performance

Benchmarked on AMD CPU (WSL2):

Metric	Value
Inference Latency	322.8 ms
Throughput	3.1 tokens/sec
Cosine Similarity vs Original	1.0000 ✅

Quick Start

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_multi-qa-mpnet-base-dot-v1.tflite")
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/multi-qa-mpnet-base-dot-v1")

def get_embedding(text: str) -> np.ndarray:
    """Get sentence embedding for input text."""
    encoded = tokenizer(
        text,
        padding="max_length",
        max_length=512,
        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,)

Files

• sentence-transformers_multi-qa-mpnet-base-dot-v1.tflite - The LiteRT model file

Conversion Details

• Conversion Tool: ai-edge-torch
• Conversion Date: 2026-01-12
• Source Framework: PyTorch → LiteRT
• Validation: Cosine similarity 1.0000 vs original

Intended Use

• Mobile Applications: On-device semantic search, RAG systems
• Edge Devices: IoT, embedded systems, Raspberry Pi
• Offline Processing: Privacy-preserving inference
• Low-latency Applications: Real-time processing

Limitations

• Fixed sequence length (512 tokens)
• CPU inference (GPU delegate requires setup)
• Tokenizer loaded separately from original model
• Float32 precision

License

This model inherits the license from the original:

• License: Apache 2.0 (source)

Citation

@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}
}

Acknowledgments

• Original model by sentence-transformers
• Conversion using ai-edge-torch

---

Converted by Bombek1