Bombek1/bge-small-en-v1.5-litert

bge-small-en-v1.5 - LiteRT

This is a LiteRT (formerly TensorFlow Lite) conversion of BAAI/bge-small-en-v1.5 for efficient on-device inference.

Model Details

Property	Value
Original Model	BAAI/bge-small-en-v1.5
Format	LiteRT (.tflite)
File Size	127.2 MB
Task	Sentence Embeddings / Retrieval
Max Sequence Length	512
Output Dimension	384
Pooling Mode	CLS Token Pooling

Performance

Benchmarked on AMD CPU (WSL2):

Metric	Value
Inference Latency	100.2 ms
Throughput	10.0/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="BAAI_bge-small-en-v1.5.tflite")
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-small-en-v1.5")

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}")  # (384,)

Files

• BAAI_bge-small-en-v1.5.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: MIT (source)

Citation

@misc{bge_embedding,
    title={C-Pack: Packaged Resources To Advance General Chinese Embedding},
    author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
    year={2023},
    eprint={2309.07597},
    archivePrefix={arXiv},
}

Acknowledgments

• Original model by BAAI
• Conversion using ai-edge-torch

---

Converted by Bombek1