MolReactGen-GuacaMol-Molecules / tokenizer_config.json
hogru's picture
Update tokenizer, bump hf versions
92eb358
raw
history blame
1.18 kB
{
"added_tokens_decoder": {
"0": {
"content": "^",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "_",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "§",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "°",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "^",
"clean_up_tokenization_spaces": true,
"eos_token": "_",
"max_length": null,
"model_max_length": 1024,
"pad_to_multiple_of": null,
"pad_token": " ",
"pad_token_type_id": 0,
"padding_side": "right",
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "left",
"unk_token": "§"
}