Integrating Uni-Mol2 with unimol_tools

[YikunHan42]

Description:
I’m working to integrate Uni-Mol2 into the unimol_tools repository and encountered some issues with configuration compatibility. I tried modifying the architecture and model configuration, as well as adjusting mol.dict to mol.dict_new.txt, but I’m not achieving the expected performance.

Here’s a summary of the integration steps I took:

1. Modified Architecture in unimol.py

   • Substituted molecule_architecture parameters to match Uni-Mol2 specifications.
   • Adjustments include reducing encoder_layers to 12, encoder_embed_dim to 768, and setting other parameters as per Uni-Mol2-84M specifications.

2. Model Configuration

   • Updated MODEL_CONFIG to point to the Uni-Mol2 checkpoint (checkpoint-84M.pt).
   • Adjusted path in weights and confirmed the correct .pt file location.

3. Dictionary Adjustment

   • Created a new dictionary file, mol.dict_new.txt, with 128 rows instead of the original 31, to match Uni-Mol2’s expected 128x128 dimension.

Observed Issue:
The model is not performing as anticipated, and the integration does not seem fully compatible with Uni-Mol2’s configuration. Specifically:

• The expected behavior and accuracy are not achieved despite matching configurations to Uni-Mol2 specs.
• Potential misalignment in the dictionary file or model configuration could be causing the issue.

Questions:

1. Could you identify any potential missteps or overlooked configuration requirements to ensure seamless integration?
2. Are there plans to add official support for Uni-Mol2 within the unimol_tools repository? This would be highly beneficial to ensure compatibility and streamline the setup process.

Steps to Reproduce:

1. Modify unimol.py as per the steps above.
2. Adjust MODEL_CONFIG to point to the checkpoint-84M.pt.
3. Replace mol.dict.txt with mol.dict_new.txt containing 128 rows.
4. Run the model and observe deviations from expected performance.

Thank you for your assistance and for considering future Uni-Mol2 support in unimol_tools!

[pansanity666]

I think the data preprocessing steps are different for Unimol2. So directly modifying the config is not OK.