Codemaster67
/

Olmo_spe_tokenizer_300SPE_TOKENS

Model card Files Files and versions

Olmo_spe_tokenizer_300SPE_TOKENS / tokenizer_config.json

Commit History

Add SPE tokenizer (434 SMILES subword tokens) + <|start_of_smiles|>/<|end_of_smiles|> special tokens. Trained on 2M ZINC20 + 2M ChEMBL canonical SMILES. SPE vocab_size=300, min_freq=4000.

9f054a4
verified

Codemaster67 commited on 6 days ago