---
{}
---

### Model Card: ChemFM Adapters for DILI Prediction on ADMET Group

**Model Overview**:  
This adapter is fine-tuned on the `DILI` dataset. It uses ChemFM as the base model and is trained on SMILES representations.

**Task Description**:  
The task a classification task, and the objective is to predict whether a drug can cause liver injury with binary labels, indicating its potential for hepatotoxicity.

**Dataset**:  
The whole dataset contains 475 samples. For more details about the dataset, visit [ADMET benchmark](https://tdcommons.ai/benchmark/admet_group/DILI).

**How to Use**:  
For more details on how to use this model, visit [ChemFM GitHub](https://github.com/TheLuoFengLab/ChemFM/tree/master/finetuning/property_prediction).