GritLM-7B 7B parameter model that uses bidirectional attention for embedding and causal attention for generation. It is finetuned from Mistral-7B 66.8 55.5 GritLM-8x7B 8x7B parameter model that uses ...
We benchmark on the community-standard Dalke NN dataset (1,000 high-similarity ChEMBL pairs) — the same dataset widely used by RDKit, CDK, and the academic MCS literature. Identical SMILES input, same ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results