llama-2-7b-finetune / tokenizer_config.json
NPap's picture
Upload tokenizer
1bf63b0
raw
history blame
1.3 kB
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<pad>",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "▁***",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"tokenizer_file": "/root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-chat-hf/snapshots/37892f30c23786c0d5367d80481fa0d9fba93cf8/tokenizer.json",
"unk_token": "<unk>",
"use_default_system_prompt": true
}