| { | |
| "add_prefix_space": false, | |
| "bos_token": { | |
| "__type": "AddedToken", | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "cls_token": { | |
| "__type": "AddedToken", | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "do_lower_case": false, | |
| "eos_token": { | |
| "__type": "AddedToken", | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "errors": "replace", | |
| "full_tokenizer_file": null, | |
| "mask_token": { | |
| "__type": "AddedToken", | |
| "content": "[MASK]", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "max_len": 512, | |
| "model_max_length": 512, | |
| "name_or_path": "DeepChem/ChemBERTa-77M-MLM", | |
| "pad_token": { | |
| "__type": "AddedToken", | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "sep_token": { | |
| "__type": "AddedToken", | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "special_tokens_map_file": "/content/drive/My Drive/Project De Novo/Molecule Transformer/SMILES_tokenized_PubChem_shard00_100k/checkpoint-60000/special_tokens_map.json", | |
| "tokenizer_class": "RobertaTokenizer", | |
| "trim_offsets": true, | |
| "unk_token": { | |
| "__type": "AddedToken", | |
| "content": "[UNK]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |