Aira-2-1B1 / tokenizer_config.json
nicholasKluge's picture
Upload tokenizer
06e0807
raw
history blame
1.98 kB
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32000": {
"content": "<|startofinstruction|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|endofcompletion|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<|endofinstruction|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<|startofinstruction|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endofcompletion|>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"padding_side": "right",
"sep_token": "<|endofinstruction|>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"tokenizer_file": "/root/.cache/huggingface/hub/models--PY007--TinyLlama-1.1B-intermediate-step-480k-1T/snapshots/098830e58452a0a08f90eb0189ec5925803fd48b/tokenizer.json",
"unk_token": "<unk>",
"use_default_system_prompt": true
}