sarashina2-70b / tokenizer_config.json
ryo0634's picture
Update tokenizer_config.json (#1)
f6959d9 verified
{
"extra_ids": 0,
"do_lower_case": false,
"keep_accents": true,
"bos_token": "<s>",
"eos_token": "</s>",
"unk_token": "<unk>",
"pad_token": "<pad>",
"mask_token": "<mask>",
"cls_token": "<cls>",
"sep_token": "<sep>",
"padding_side": "left",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"tokenizer_class": "LlamaTokenizer",
"added_tokens_decoder": {
"4": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"5": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"6": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"7": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"8": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"9": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"10": {
"content": "<|available_tools|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"11": {
"content": "<|tool_calls|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"12": {
"content": "<|tool_results|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"13": {
"content": "<|code|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"14": {
"content": "<|file|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"102397": {
"content": "<|prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"102398": {
"content": "<|suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"102399": {
"content": "<|middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"add_prefix_space": false,
"add_dummy_prefix_space": false,
"legacy": false,
"add_bos_token": false,
"add_eos_token": false
}