schrodinger.application.matsci.flywheel.ldmol.text_encoder module¶
ONNX-based text encoder for MolT5.
- class schrodinger.application.matsci.flywheel.ldmol.text_encoder.MolT5TextEncoder(device='cpu', logger=None)¶
Bases:
BaseModelMolT5 text encoder using ONNX Runtime.
Replaces transformers.T5EncoderModel to eliminate the external dependency. Model is loaded lazily on first use.
- __init__(device='cpu', logger=None)¶
- Parameters:
device (str) – Device for inference
logger – Logger instance for debug output
- ensureModelLoaded()¶
Load ONNX encoder model on first use.
- encode(descriptions)¶
Encode text descriptions into latent embeddings.
- Parameters:
descriptions (list(str)) – Text descriptions
- Return type:
tuple(numpy.ndarray, numpy.ndarray)
- Returns:
encoder_outputs and attention_mask