---
license: apache-2.0
datasets:
- sentence-transformers/natural-questions
language:
- en
base_model: cross-encoder/ms-marco-MiniLM-L12-v2
pipeline_tag: text-ranking
library_name: rk-transformers
tags:
- transformers
- rknn
- rockchip
- npu
- rk-transformers
- rk3588
model_name: ms-marco-MiniLM-L12-v2
---
# ms-marco-MiniLM-L12-v2 (RKNN2)

> This is an RKNN-compatible version of the [cross-encoder/ms-marco-MiniLM-L12-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L12-v2) model. It has been optimized for Rockchip NPUs using the [rk-transformers](https://github.com/emapco/rk-transformers) library.

<details><summary>Click to see the RKNN model details and usage examples</summary>

## Model Details

- **Original Model:** [cross-encoder/ms-marco-MiniLM-L12-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L12-v2)
- **Target Platform:** rk3588
- **rknn-toolkit2 Version:** 2.3.2
- **rk-transformers Version:** 0.3.0

### Available Model Files

| Model File | Optimization Level | Quantization | File Size |
| :--------- | :----------------- | :----------- | :-------- |
| [model.rknn](./model.rknn) | 0 | float16 | 68.8 MB |
| [model_b1_s256.rknn](./model_b1_s256.rknn) | 0 | float16 | 67.0 MB |
| [model_b4_s256.rknn](./model_b4_s256.rknn) | 0 | float16 | 75.1 MB |
| [model_b4_s512.rknn](./model_b4_s512.rknn) | 0 | float16 | 81.7 MB |
| [rknn/model_o1.rknn](./rknn/model_o1.rknn) | 1 | float16 | 68.8 MB |
| [rknn/model_o2.rknn](./rknn/model_o2.rknn) | 2 | float16 | 68.8 MB |
| [rknn/model_o3.rknn](./rknn/model_o3.rknn) | 3 | float16 | 68.8 MB |
| [rknn/model_w8a8.rknn](./rknn/model_w8a8.rknn) | 0 | w8a8 | 36.5 MB |

## Usage

### Installation

Install `rk-transformers` with inference dependencies to use this model:

```bash
pip install rk-transformers[inference]
```

#### RK-Transformers API

```python
from rktransformers import RKModelForSequenceClassification
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("rk-transformers/ms-marco-MiniLM-L12-v2")
model = RKModelForSequenceClassification.from_pretrained(
    "rk-transformers/ms-marco-MiniLM-L12-v2",
    platform="rk3588",
    core_mask="auto",
)

inputs = tokenizer("Hello, my dog is cute", return_tensors="np")
outputs = model(**inputs)
logits = outputs.logits
print(logits.shape)

# Load specific optimized/quantized model file
model = RKModelForSequenceClassification.from_pretrained(
    "rk-transformers/ms-marco-MiniLM-L12-v2",
    platform="rk3588",
    file_name="rknn/model_w8a8.rknn"
)
```

## Configuration

The full configuration for all exported RKNN models is available in the [config.json](./config.json) file.

</details>

---
# Cross-Encoder for MS Marco

This model was trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task.

The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/cross_encoder/training/ms_marco)


## Usage with SentenceTransformers

The usage is easy when you have [SentenceTransformers](https://www.sbert.net/) installed. Then you can use the pre-trained models like this:
```python
from sentence_transformers import CrossEncoder

model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L12-v2')
scores = model.predict([
    ("How many people live in Berlin?", "Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers."),
    ("How many people live in Berlin?", "Berlin is well known for its museums."),
])
print(scores)
# [ 9.218911  -4.0780287]
```


## Usage with Transformers

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/ms-marco-MiniLM-L12-v2')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/ms-marco-MiniLM-L12-v2')

features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'],  padding=True, truncation=True, return_tensors="pt")

model.eval()
with torch.no_grad():
    scores = model(**features).logits
    print(scores)
```



## Performance
In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [TREC Deep Learning 2019](https://microsoft.github.io/TREC-2019-Deep-Learning/) and the [MS Marco Passage Reranking](https://github.com/microsoft/MSMARCO-Passage-Ranking/) dataset. 


| Model-Name        | NDCG@10 (TREC DL 19) | MRR@10 (MS Marco Dev)  | Docs / Sec |
| ------------- |:-------------| -----| --- | 
| **Version 2 models** | | | 
| cross-encoder/ms-marco-TinyBERT-L2-v2 | 69.84 | 32.56 | 9000
| cross-encoder/ms-marco-MiniLM-L2-v2 | 71.01 | 34.85 | 4100
| cross-encoder/ms-marco-MiniLM-L4-v2 | 73.04 | 37.70 | 2500
| cross-encoder/ms-marco-MiniLM-L6-v2 | 74.30 | 39.01 | 1800
| cross-encoder/ms-marco-MiniLM-L12-v2 | 74.31 | 39.02 | 960
| **Version 1 models** | | | 
| cross-encoder/ms-marco-TinyBERT-L2  | 67.43 | 30.15  | 9000
| cross-encoder/ms-marco-TinyBERT-L4  | 68.09 | 34.50  | 2900
| cross-encoder/ms-marco-TinyBERT-L6 |  69.57 | 36.13  | 680
| cross-encoder/ms-marco-electra-base | 71.99 | 36.41 | 340
| **Other models** | | | 
| nboost/pt-tinybert-msmarco | 63.63 | 28.80 | 2900 
| nboost/pt-bert-base-uncased-msmarco | 70.94 | 34.75 | 340 
| nboost/pt-bert-large-msmarco | 73.36 | 36.48 | 100 
| Capreolus/electra-base-msmarco | 71.23 | 36.89 | 340 
| amberoad/bert-multilingual-passage-reranking-msmarco | 68.40 | 35.54 | 330 
| sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco | 72.82 | 37.88 | 720
 
 Note: Runtime was computed on a V100 GPU.