ibm-research/materials.smi-ted
https://huggingface.co/ibm-research/materials.smi-tedWelcome to IBM's series of large foundation models for sustainable materials. Our models span a variety of representations and modalities, including SMILES, SELFIES, 3D atom positions, 3D density grids, molecular graphs, and other formats.
Sourced from
- HuggingFace — ibm-research/materials.smi-ted
Related resources
# ChemGPT 4.7M ChemGPT is based on the GPT-Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models.
HauserGroup/ApeTokenizer-SMILES
by HauserGroupApeTokenizer-SMILES is an Atom Pair Encoding (APE) tokenizer for SMILES strings, trained on ~2M unique canonical SMILES from ChEMBL 36. It is the SMILES counterpart to ApeTokenizer-SELFIES, released alongside ModernMolBERT.
Hari5115/molecular-odor-predictor
by Hari5115A PyTorch MLP that predicts odor descriptors from a molecule's SMILES string using Morgan (ECFP4) fingerprints. Given any molecule, the model outputs a smell profile across 50 odor categories.
In recent years, pre-trained language models (PLMs) achieve the best performance on a wide range of natural language processing (NLP) tasks. While the first models were trained on general domain data, specialized ones have emerged to more effectively treat specific domains.
# ChemGPT 1.2B ChemGPT is based on the GPT-Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models.
fairydance/molexar-10m-base
by fairydanceMolexar-10M Base is the unconditional base model for Molexar, a unified multimodal molecular foundation model for drug design. It is trained as an autoregressive molecular language model over Fragment-SELFIES, a BRICS-fragment molecular language with validity-preserving decoding and…