metadata
tags:
- torch_molecule
- molecular-property-prediction
library_name: torch_molecule
MoamaMolecularEncoder Model
Model Description
- Model Type: MoamaMolecularEncoder
- Framework: torch_molecule
- Last Updated: 2025-08-07
Task Summary
| Task | Version | Last Updated | Parameters | Metrics |
|---|---|---|---|---|
| default | 0.0.10 | 2025-08-07 | 3,832,927 |
Usage
from torch_molecule import MoamaMolecularEncoder
# Load model for specific task
model = MoamaMolecularEncoder()
model.load(
"local_model_dir/MoamaMolecularEncoder.pt",
repo="Do1Yun/TorchMoleculeEncoderRepo"
)
# For predictor: Make predictions
# predictions = model.predict(smiles_list)
# For generator: Make generations
# generations = model.generate(n_samples)
# For encoder: Make encodings
# encodings = model.encode(smiles_list)
Tasks Details
default Task
- Current Version: 0.0.10
- Last Updated: 2025-08-07
- Parameters: 3,832,927
- Configuration:
{
"mask_rate": 0.15,
"lw_rec": 0.5,
"encoder_type": "gin-virtual",
"readout": "sum",
"num_layer": 5,
"hidden_size": 300,
"drop_ratio": 0.5,
"norm_layer": "batch_norm",
"batch_size": 32,
"epochs": 10,
"learning_rate": 0.001,
"weight_decay": 0.0,
"grad_clip_value": null,
"use_lr_scheduler": false,
"scheduler_factor": 0.5,
"scheduler_patience": 5,
"fitting_epoch": 9,
"device": {
"_type": "unknown",
"repr": "cuda:0"
},
"verbose": false,
"model_name": "MoamaMolecularEncoder"
}