llemma-7b-v4-finetuned-small-chunks / tokenizer_config.json
piercemaloney's picture
Upload tokenizer
62a1c23 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
},
"7528": {
"content": "*)",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10456": {
"content": "(*",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"(*",
"*)"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}