---
tags:
- litert
- tflite
- on-device
- sentence-transformer
license: apache-2.0
base_model: pritamdeka/S-PubMedBert-MS-MARCO
---

# pritamdeka/S-PubMedBert-MS-MARCO - LiteRT Optimized

This is a [LiteRT](https://ai.google.dev/edge/litert) (formerly TensorFlow Lite) export of [pritamdeka/S-PubMedBert-MS-MARCO](https://huggingface.co/pritamdeka/S-PubMedBert-MS-MARCO).

It is optimized for mobile and edge inference (Android/iOS/Embedded).

## Model Details
| Attribute | Value |
| :--- | :--- |
| **Task** | Medical Sentence Embeddings |
| **Format** | `.tflite` (Float32) |
| **File Size** | 415.9 MB |
| **Input Length** | 512 tokens |
| **Output Dim** | 768 |

## Usage

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

# Load model
interpreter = Interpreter(model_path="pritamdeka_S-PubMedBert-MS-MARCO.tflite")
interpreter.allocate_tensors()

tokenizer = AutoTokenizer.from_pretrained("pritamdeka/S-PubMedBert-MS-MARCO")

def get_embedding(text):
    inputs = tokenizer(text, max_length=512, padding="max_length", truncation=True, return_tensors="np")

    input_details = interpreter.get_input_details()
    interpreter.set_tensor(input_details[0]['index'], inputs['input_ids'].astype(np.int64))
    interpreter.set_tensor(input_details[1]['index'], inputs['attention_mask'].astype(np.int64))

    interpreter.invoke()

    output_details = interpreter.get_output_details()
    return interpreter.get_tensor(output_details[0]['index'])[0]

emb = get_embedding("Hello world")
print(f"Embedding shape: {emb.shape}")
```

*Converted by [Bombek1](https://huggingface.co/Bombek1) using [litert-torch](https://github.com/google-ai-edge/ai-edge-torch)*