Files
Franso-reinvent_229M_256_prior/tokenizer_config.json

49 lines
1.0 KiB
JSON
Raw Permalink Normal View History

{
"added_tokens_decoder": {
"256": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"257": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"258": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"259": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}