mist-28M-0uiq7o7m-freesolv / tokenizer_config.json
anoushka2000's picture
Upload folder using huggingface_hub
9905e27 verified
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"159": {
"content": "[BOS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"160": {
"content": "[EOS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"161": {
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"162": {
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"163": {
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"164": {
"content": "[MASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "[BOS]",
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"eos_token": "[EOS]",
"extra_special_tokens": {},
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "SmirkTokenizerFast",
"unk_token": "[UNK]",
"vocab_file": "/nfs/turbo/coe-venkvis/abhutani/electrolyte-fm/.venv/lib/python3.10/site-packages/smirk/vocab_smiles.json"
}