update readme

Author: liugangcode

README.md

@@ -19,10 +19,6 @@
 
 `torch-molecule` is a package under active development that facilitates molecular discovery through deep learning, featuring a user-friendly, `sklearn`-style interface. It includes model checkpoints for efficient deployment and benchmarking across a range of molecular tasks. Currently, the package focuses on three main components:
 
-Here are the three Markdown tables, each showing only the models you have already supported for each category:
-
-Below are three Markdown tables that list only the supported models. Each table includes a column for the model name and a column for its reference. Since specific references were not provided, a placeholder "[Reference unknown]" is used. 
-
 1. **Predictive Models**: Done: GREA, SGIR, IRM, GIN/GCN w/ virtual, DIR. TODO: SMILES-based LSTM/Transformers, more
 2. **Generative Models**: Done: Graph DiT, GraphGA, DiGress. TODO:, GDSS, more
 3. **Representation Models**: Done: MoAMa, AttrMasking, ContextPred, EdgePred. Many pretrained models from HF. TODO: checkpoints, more