samantha-1-tokenizer / tokenizer_config.json
sidbin's picture
Upload tokenizer
92d09c7 verified
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|im_start|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_token_0>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32003": {
"content": "<extra_token_1>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32004": {
"content": "<extra_token_2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32005": {
"content": "<extra_token_3>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32006": {
"content": "<extra_token_4>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32007": {
"content": "<extra_token_5>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32008": {
"content": "<extra_token_6>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32009": {
"content": "<extra_token_7>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32010": {
"content": "<extra_token_8>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32011": {
"content": "<extra_token_9>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32012": {
"content": "<extra_token_10>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32013": {
"content": "<extra_token_11>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32014": {
"content": "<extra_token_12>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32015": {
"content": "<extra_token_13>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32016": {
"content": "<extra_token_14>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32017": {
"content": "<extra_token_15>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32018": {
"content": "<extra_token_16>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32019": {
"content": "<extra_token_17>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32020": {
"content": "<extra_token_18>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32021": {
"content": "<extra_token_19>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32022": {
"content": "<extra_token_20>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32023": {
"content": "<extra_token_21>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32024": {
"content": "<extra_token_22>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32025": {
"content": "<extra_token_23>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32026": {
"content": "<extra_token_24>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32027": {
"content": "<extra_token_25>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32028": {
"content": "<extra_token_26>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32029": {
"content": "<extra_token_27>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32030": {
"content": "<extra_token_28>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32031": {
"content": "<extra_token_29>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{%\n if not add_generation_prompt is defined\n %}{%\n set add_generation_prompt = false\n %}{% \n endif\n%}{% \n for message in messages\n %}<|im_start|>{%\n if message.role == 'system'\n %}{{message.name or 'situation'}}{%\n else\n %}{%\n if message.role == \"user\"\n %}person{%\n elif message.role == \"assistant\"\n %}me{%\n else\n %}{{message.role}}{%\n endif\n %}{%\n if message.name\n %} ({{message.name}}){%\n endif\n %}{%\n endif\n %}{{'\n' + message.content}}{%\n if not loop.last\n %}<|im_end|>\n{%\n elif add_generation_prompt\n and not message.continue\n %}<|im_end|>\n<|im_start|>me\n{%\n endif\n %}{%\n endfor\n%}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"trust_remote_code": false,
"unk_token": "<unk>",
"use_default_system_prompt": true,
"use_fast": true
}