TeenyTinyLlama-160m-HateBR / tokenizer_config.json
nicholasKluge's picture
Training in progress, epoch 1
840b6c0
raw
history blame
1.12 kB
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"bos_token_id": 1,
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eos_token_id": 2,
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"pad_token_id": 3,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"unk_token_id": 0,
"use_default_system_prompt": false
}