Skip to main content

Installation

To begin using the GLiNER model, you can install the GLiNER Python library through pip, conda, or directly from the source.

Install via Pip​

pip install gliner
ONNX runtime

If you intend to use the GPU-backed ONNX runtime, install GLiNER with the GPU feature. This also installs the onnxruntime-gpu dependency.

pip install gliner[gpu]

Install via Conda​

conda install -c conda-forge gliner

Install from Source​

To install the GLiNER library from source, follow these steps:

  1. Clone the Repository:

    First, clone the GLiNER repository from GitHub:

    git clone https://github.com/urchade/GLiNER

  2. Navigate to the Project Directory:

    Change to the directory containing the cloned repository:

    cd GLiNER

  3. Install Dependencies:

    tip

    It's a good practice to create and activate a virtual environment before installing dependencies:

    python -m venv venv
    source venv/bin/activate   # On Windows use: venv\Scripts\activate

    Install the required dependencies listed in the requirements.txt file:

    pip install -r requirements.txt

  4. Install the GLiNER Package:

    Finally, install the GLiNER package using the setup script:

    pip install .

  5. Verify Installation:

    You can verify the installation by importing the library in a Python script:

    import gliner
    print(gliner.__version__)

Install FlashDeBERTa​

Most GLiNER models use the DeBERTa encoder as their backbone. This architecture offers strong token classification performance and typically requires less data to achieve good results. However, a major drawback has been its slower inference speed. We developed FlashDeBERTa to combine the good performance of the model and bring a new level of efficiency.

To use FlashDeBERTa with GLiNER, install it:

pip install flashdeberta -U
tip

Before using FlashDeBERTa, please make sure that you have transformers>=4.47.0.

You need to export the environment variable to enable the usage of FlashDeBERTa: export USE_FLASHDEBERTA=1. And then you can export the GLiNER model, and it will automatically use FlashDeBERTa kernels.

model = GLiNER.from_pretrained("knowledgator/gliner-pii-large-v1.0")

FlashDeBERTa provides up to a 3× speed boost for typical sequence lengths—and even greater improvements for longer sequences. alt text