README.md

---
license: apache-2.0
pipeline_tag: text-ranking
language:
- en
library_name: sentence-transformers
base_model:
- google/electra-large-discriminator
tags:
- transformers
---

## Cross-Encoder for Text Ranking

This model is a port of the [webis/monoelectra-large](https://huggingface.co/webis/monoelectra-large) model from [lightning-ir](https://github.com/webis-de/lightning-ir) to [Sentence Transformers](https://sbert.net/) and [Transformers](https://huggingface.co/docs/transformers). 

The original model was introduced in the paper [A Systematic Investigation of Distilling Large Language Models into Cross-Encoders for Passage Re-ranking](https://arxiv.org/abs/2405.07920). See https://github.com/webis-de/rank-distillm for code used to train the original model.

The model can be used as a reranker in a 2-stage "retrieve-rerank" pipeline, where it reorders passages returned by a retriever model (e.g. an embedding model or BM25) given some query. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details.

## Usage with Sentence Transformers

The usage is easy when you have [SentenceTransformers](https://www.sbert.net/) installed. 

```bash
pip install sentence-transformers
```

Then you can use the pre-trained model like this:

```python
from sentence_transformers import CrossEncoder

model = CrossEncoder("cross-encoder/monoelectra-large", trust_remote_code=True)
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)
# [ 6.016401  -3.6922567]
```

## Usage with Transformers

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

model = AutoModelForSequenceClassification.from_pretrained("cross-encoder/monoelectra-large", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("cross-encoder/monoelectra-large")

features = tokenizer(
    [
        ("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."),
    ],
    padding=True,
    truncation=True,
    return_tensors="pt",
)

model.eval()
with torch.no_grad():
    scores = model(**features).logits.view(-1)
print(scores)
# tensor([ 6.0164, -3.6923])
```