sma-chemsitry-pretrained / tokenizer_config.json
jxie's picture
Upload tokenizer
4696369 verified
{
"bos_token": {
"__type": "AddedToken",
"content": "[BOS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "[EOS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "/iris/u/jwxie/workspace/releases/domain-agnostic-pretraining/examples/saved_models/chem_pretrained/chem_guided_self_rand_select_masking_recon_base_noise_mask_self_random_mix-adamw_torch-lr1e-4-wd0.01-ws10000-mr0.3-sep_merge",
"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": "/iris/u/jwxie/workspace/releases/domain-agnostic-pretraining/examples/saved_models/chem_pretrained/chem_guided_self_rand_select_masking_recon_base_noise_mask_self_random_mix-adamw_torch-lr1e-4-wd0.01-ws10000-mr0.3-sep_merge/special_tokens_map.json",
"tokenizer_class": "SMATokenizer"
}