Derify/ChemMRL
Sentence Similarity
•
0.2B
•
Updated
•
1.18k
ChemMRL
SMILES Matryoshka Representation Learning Embedding Transformer
-
Derify/pubchem_10m_genmol_similarity
Viewer • Updated • 21M • 165Note A SMILES-pair dataset for training ChemMRL via knowledge distillation from GenMol. Each molecule is paired with a valid, similar variant and similarity label to enable molecular similarity, retrieval, clustering, and other cheminformatics tasks.
-
Chem-MRL Demo
⚛1Search for similar molecules using SMILES or a canvas
-
Derify/ChemMRL-beta
Sentence Similarity • 0.2B • Updated • 431 -
Derify/ChemMRL-alpha
Sentence Similarity • 0.2B • Updated • 131