bge-reranker-base-fp16-ov

bge-reranker-base-fp16-ov

• Model creator: BAAI
• Original model: bge-reranker-base

Description

This is bge-reranker-base model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to FP16.

Compatibility

The provided OpenVINO™ IR model is compatible with:

• OpenVINO version 2025.3.0 and higher
• Optimum Intel 1.25.2 and higher

Running Model Inference with Optimum Intel

1. Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install optimum[openvino]

1. Run model inference:

from transformers import AutoTokenizer
from optimum.intel import OVModelForSequenceClassification


tokenizer = AutoTokenizer.from_pretrained('OpenVINO/bge-reranker-base-fp16-ov')
model = OVModelForSequenceClassification.from_pretrained('OpenVINO/bge-reranker-base-fp16-ov')

pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]

inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
print(scores)

For more examples and possible optimizations, refer to the Inference with Optimum Intel.

You can find more detailed usage examples in OpenVINO Notebooks:

• RAG text generation

Running Model with Cohere client and OpenVINO Model Server

1a. Deploy model on Windows using binary package:

mkdir C:\models
ovms.exe --rest_port 8000 --source_model OpenVINO/bge-reranker-base-fp16-ov --model_repository_path C:\models

1b. Deploy model in a Docker container:

mkdir -p ${HOME}/models
export GPU_ARGS=$(if ls /dev/dri/render* >/dev/null 2>&1; then echo "--device /dev/dri --group-add $(stat -c '%g' /dev/dri/render* | head -n1)"; fi)
docker run -d ${GPU_ARGS} --rm --user $(id -u):$(id -g) -p 8000:8000 -v ${HOME}/models:/models openvino/model_server:latest-gpu --rest_port 8000 --model_repository_path /models --source_model OpenVINO/bge-reranker-base-fp16-ov

1. Install the client library:

pip install cohere

1. Run the client:

import cohere

client = cohere.Client(base_url="http://localhost:8000/v1", api_key="not_used")

query = "What is the capital of France?"
documents = [
    "Paris is the capital city of France.",
    "Berlin is the capital city of Germany.",
]

response = client.rerank(
    model="OpenVINO/bge-reranker-base-fp16-ov",
    query=query,
    documents=documents,
)

for result in response.results:
    print(result.index, result.relevance_score)

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under MIT license. More details can be found in bge-reranker-base.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.