codellama_extraction / tokenizer_config.json
mibruel's picture
Upload tokenizer
f22ea45 verified
raw
history blame
1.9 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": 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
},
"32000": {
"content": "▁<PRE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "▁<MID>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "▁<SUF>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "▁<EOT>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>",
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eot_token": "▁<EOT>",
"fill_token": "<FILL_ME>",
"legacy": null,
"middle_token": "▁<MID>",
"model_max_length": 16384,
"pad_token": "<unk>",
"padding_side": "left",
"prefix_token": "▁<PRE>",
"sp_model_kwargs": {},
"suffix_token": "▁<SUF>",
"tokenizer_class": "CodeLlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}