codellama_utests_full_new_ver2 / tokenizer_config.json
Utkarsh524's picture
Upload folder using huggingface_hub
83045e4 verified
{
"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
},
"32007": {
"content": "▁<PRE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "▁<SUF>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "▁<MID>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "▁<EOT>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|system|>",
"<|user|>",
"<|assistant|>",
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eot_token": "▁<EOT>",
"extra_special_tokens": {},
"fill_token": "<FILL_ME>",
"legacy": null,
"max_length": 4096,
"middle_token": "▁<MID>",
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "</s>",
"pad_token_type_id": 0,
"padding_side": "left",
"prefix_token": "▁<PRE>",
"sp_model_kwargs": {},
"stride": 0,
"suffix_token": "▁<SUF>",
"tokenizer_class": "CodeLlamaTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}