Download tokenizer.json from hothousetx/smiles_t5: direct link, hf CLI and curl.
- Browser
- Download file 37.5 kB
-
https://huggingface.co/hothousetx/smiles_t5/resolve/main/tokenizer.json
- Command line
-
hf download hf://hothousetx/smiles_t5/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/hothousetx/smiles_t5/resolve/main/tokenizer.json
37.5 kB
| { | |
| "version": "1.0", | |
| "truncation": { | |
| "direction": "Right", | |
| "max_length": 2048, | |
| "strategy": "LongestFirst", | |
| "stride": 0 | |
| }, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "<pad>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "</s>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "<unk>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 53, | |
| "content": "<extra_id_0>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 54, | |
| "content": "<extra_id_1>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 55, | |
| "content": "<extra_id_2>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 56, | |
| "content": "<extra_id_3>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 57, | |
| "content": "<extra_id_4>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 58, | |
| "content": "<extra_id_5>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 59, | |
| "content": "<extra_id_6>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 60, | |
| "content": "<extra_id_7>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 61, | |
| "content": "<extra_id_8>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 62, | |
| "content": "<extra_id_9>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 63, | |
| "content": "<extra_id_10>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 64, | |
| "content": "<extra_id_11>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 65, | |
| "content": "<extra_id_12>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 66, | |
| "content": "<extra_id_13>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 67, | |
| "content": "<extra_id_14>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 68, | |
| "content": "<extra_id_15>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 69, | |
| "content": "<extra_id_16>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 70, | |
| "content": "<extra_id_17>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 71, | |
| "content": "<extra_id_18>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 72, | |
| "content": "<extra_id_19>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 73, | |
| "content": "<extra_id_20>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 74, | |
| "content": "<extra_id_21>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 75, | |
| "content": "<extra_id_22>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 76, | |
| "content": "<extra_id_23>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 77, | |
| "content": "<extra_id_24>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 78, | |
| "content": "<extra_id_25>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 79, | |
| "content": "<extra_id_26>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 80, | |
| "content": "<extra_id_27>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 81, | |
| "content": "<extra_id_28>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 82, | |
| "content": "<extra_id_29>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 83, | |
| "content": "<extra_id_30>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 84, | |
| "content": "<extra_id_31>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 85, | |
| "content": "<extra_id_32>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 86, | |
| "content": "<extra_id_33>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 87, | |
| "content": "<extra_id_34>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 88, | |
| "content": "<extra_id_35>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 89, | |
| "content": "<extra_id_36>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 90, | |
| "content": "<extra_id_37>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 91, | |
| "content": "<extra_id_38>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 92, | |
| "content": "<extra_id_39>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 93, | |
| "content": "<extra_id_40>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 94, | |
| "content": "<extra_id_41>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 95, | |
| "content": "<extra_id_42>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 96, | |
| "content": "<extra_id_43>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 97, | |
| "content": "<extra_id_44>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 98, | |
| "content": "<extra_id_45>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 99, | |
| "content": "<extra_id_46>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 100, | |
| "content": "<extra_id_47>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 101, | |
| "content": "<extra_id_48>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 102, | |
| "content": "<extra_id_49>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 103, | |
| "content": "<extra_id_50>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 104, | |
| "content": "<extra_id_51>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 105, | |
| "content": "<extra_id_52>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 106, | |
| "content": "<extra_id_53>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 107, | |
| "content": "<extra_id_54>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 108, | |
| "content": "<extra_id_55>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 109, | |
| "content": "<extra_id_56>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 110, | |
| "content": "<extra_id_57>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 111, | |
| "content": "<extra_id_58>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 112, | |
| "content": "<extra_id_59>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 113, | |
| "content": "<extra_id_60>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 114, | |
| "content": "<extra_id_61>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 115, | |
| "content": "<extra_id_62>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 116, | |
| "content": "<extra_id_63>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 117, | |
| "content": "<extra_id_64>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 118, | |
| "content": "<extra_id_65>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 119, | |
| "content": "<extra_id_66>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 120, | |
| "content": "<extra_id_67>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 121, | |
| "content": "<extra_id_68>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 122, | |
| "content": "<extra_id_69>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 123, | |
| "content": "<extra_id_70>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 124, | |
| "content": "<extra_id_71>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 125, | |
| "content": "<extra_id_72>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 126, | |
| "content": "<extra_id_73>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 127, | |
| "content": "<extra_id_74>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 128, | |
| "content": "<extra_id_75>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 129, | |
| "content": "<extra_id_76>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 130, | |
| "content": "<extra_id_77>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 131, | |
| "content": "<extra_id_78>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 132, | |
| "content": "<extra_id_79>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 133, | |
| "content": "<extra_id_80>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 134, | |
| "content": "<extra_id_81>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 135, | |
| "content": "<extra_id_82>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 136, | |
| "content": "<extra_id_83>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 137, | |
| "content": "<extra_id_84>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 138, | |
| "content": "<extra_id_85>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 139, | |
| "content": "<extra_id_86>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 140, | |
| "content": "<extra_id_87>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 141, | |
| "content": "<extra_id_88>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 142, | |
| "content": "<extra_id_89>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 143, | |
| "content": "<extra_id_90>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 144, | |
| "content": "<extra_id_91>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 145, | |
| "content": "<extra_id_92>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 146, | |
| "content": "<extra_id_93>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 147, | |
| "content": "<extra_id_94>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 148, | |
| "content": "<extra_id_95>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 149, | |
| "content": "<extra_id_96>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 150, | |
| "content": "<extra_id_97>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 151, | |
| "content": "<extra_id_98>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 152, | |
| "content": "<extra_id_99>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 153, | |
| "content": "fr_C_O", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 154, | |
| "content": "fr_C_O_noCOO", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 155, | |
| "content": "fr_Al_OH", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 156, | |
| "content": "fr_Ar_OH", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 157, | |
| "content": "fr_methoxy", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 158, | |
| "content": "fr_oxime", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 159, | |
| "content": "fr_ester", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 160, | |
| "content": "fr_Al_COO", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 161, | |
| "content": "fr_Ar_COO", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 162, | |
| "content": "fr_COO", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 163, | |
| "content": "fr_COO2", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 164, | |
| "content": "fr_ketone", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 165, | |
| "content": "fr_ether", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 166, | |
| "content": "fr_phenol", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 167, | |
| "content": "fr_aldehyde", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 168, | |
| "content": "fr_quatN", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 169, | |
| "content": "fr_NH2", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 170, | |
| "content": "fr_NH1", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 171, | |
| "content": "fr_NH0", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 172, | |
| "content": "fr_Ar_N", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 173, | |
| "content": "fr_Ar_NH", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 174, | |
| "content": "fr_aniline", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 175, | |
| "content": "fr_Imine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 176, | |
| "content": "fr_nitrile", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 177, | |
| "content": "fr_hdrzine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 178, | |
| "content": "fr_hdrzone", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 179, | |
| "content": "fr_nitroso", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 180, | |
| "content": "fr_N_O", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 181, | |
| "content": "fr_nitro", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 182, | |
| "content": "fr_azo", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 183, | |
| "content": "fr_diazo", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 184, | |
| "content": "fr_azide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 185, | |
| "content": "fr_amide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 186, | |
| "content": "fr_priamide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 187, | |
| "content": "fr_amidine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 188, | |
| "content": "fr_guanido", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 189, | |
| "content": "fr_Nhpyrrole", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 190, | |
| "content": "fr_imide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 191, | |
| "content": "fr_isocyan", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 192, | |
| "content": "fr_isothiocyan", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 193, | |
| "content": "fr_thiocyan", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 194, | |
| "content": "fr_halogen", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 195, | |
| "content": "fr_alkyl_halide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 196, | |
| "content": "fr_sulfide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 197, | |
| "content": "fr_SH", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 198, | |
| "content": "fr_C_S", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 199, | |
| "content": "fr_sulfone", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 200, | |
| "content": "fr_sulfonamd", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 201, | |
| "content": "fr_prisulfonamd", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 202, | |
| "content": "fr_barbitur", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 203, | |
| "content": "fr_urea", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 204, | |
| "content": "fr_term_acetylene", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 205, | |
| "content": "fr_imidazole", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 206, | |
| "content": "fr_furan", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 207, | |
| "content": "fr_thiophene", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 208, | |
| "content": "fr_thiazole", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 209, | |
| "content": "fr_oxazole", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 210, | |
| "content": "fr_pyridine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 211, | |
| "content": "fr_piperdine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 212, | |
| "content": "fr_piperzine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 213, | |
| "content": "fr_morpholine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 214, | |
| "content": "fr_lactam", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 215, | |
| "content": "fr_lactone", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 216, | |
| "content": "fr_tetrazole", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 217, | |
| "content": "fr_epoxide", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 218, | |
| "content": "fr_unbrch_alkane", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 219, | |
| "content": "fr_bicyclic", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 220, | |
| "content": "fr_benzene", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 221, | |
| "content": "fr_phos_acid", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 222, | |
| "content": "fr_phos_ester", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 223, | |
| "content": "fr_nitro_arom", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 224, | |
| "content": "fr_nitro_arom_nonortho", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 225, | |
| "content": "fr_dihydropyridine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 226, | |
| "content": "fr_phenol_noOrthoHbond", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 227, | |
| "content": "fr_Al_OH_noTert", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 228, | |
| "content": "fr_benzodiazepine", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 229, | |
| "content": "fr_para_hydroxylation", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 230, | |
| "content": "fr_allylic_oxid", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 231, | |
| "content": "fr_aryl_methyl", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 232, | |
| "content": "fr_Ndealkylation1", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 233, | |
| "content": "fr_Ndealkylation2", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 234, | |
| "content": "fr_alkyl_carbamate", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 235, | |
| "content": "fr_ketone_Topliss", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 236, | |
| "content": "fr_ArN", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 237, | |
| "content": "fr_HOCCN", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 238, | |
| "content": "scaffold:", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| }, | |
| { | |
| "id": 239, | |
| "content": "fragments:", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": true, | |
| "special": false | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|-|\\+|\\\\|\\/|:|~|@|\\?|>>?|\\*|\\$|\\%[0-9]{2}|[0-9])" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "</s>": { | |
| "id": "</s>", | |
| "ids": [ | |
| 1 | |
| ], | |
| "tokens": [ | |
| "</s>" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "<pad>": 0, | |
| "</s>": 1, | |
| "<unk>": 2, | |
| "C": 3, | |
| "c": 4, | |
| "(": 5, | |
| ")": 6, | |
| "1": 7, | |
| "O": 8, | |
| "N": 9, | |
| "=": 10, | |
| "2": 11, | |
| "n": 12, | |
| "\n": 13, | |
| "[C@H]": 14, | |
| "[C@@H]": 15, | |
| "3": 16, | |
| "F": 17, | |
| "o": 18, | |
| "[nH]": 19, | |
| "S": 20, | |
| "s": 21, | |
| "#": 22, | |
| "Cl": 23, | |
| "-": 24, | |
| "4": 25, | |
| "/": 26, | |
| "[C@]": 27, | |
| "[C@@]": 28, | |
| "[O-]": 29, | |
| "[N+]": 30, | |
| "\\": 31, | |
| "Br": 32, | |
| "[S@]": 33, | |
| "[S@@]": 34, | |
| "5": 35, | |
| "[n+]": 36, | |
| "I": 37, | |
| "[Si]": 38, | |
| "P": 39, | |
| "B": 40, | |
| "[CH]": 41, | |
| "6": 42, | |
| "[C]": 43, | |
| "[N-]": 44, | |
| "7": 45, | |
| "[C-]": 46, | |
| "[CH2]": 47, | |
| "[P@]": 48, | |
| "[S+]": 49, | |
| "[N@+]": 50, | |
| "[S@+]": 51, | |
| "[s+]": 52 | |
| }, | |
| "unk_token": "<unk>" | |
| } | |
| } |