Transformers
superbpe-experimental_v0.1.0 / tokenizer_config.json
undfined's picture
Fix decoder
f498593 verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"180000": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"180001": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"180002": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180003": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180004": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180005": {
"content": "|||PHONE_NUMBER|||",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180006": {
"content": "|||EMAIL_ADDRESS|||",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180007": {
"content": "|||IP_ADDRESS|||",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180008": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180009": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180010": {
"content": "<|extra_id_0|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180011": {
"content": "<|extra_id_1|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180012": {
"content": "<|extra_id_2|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180013": {
"content": "<|extra_id_3|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180014": {
"content": "<|extra_id_4|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180015": {
"content": "<|extra_id_5|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180016": {
"content": "<|extra_id_6|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180017": {
"content": "<|extra_id_7|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180018": {
"content": "<|extra_id_8|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180019": {
"content": "<|extra_id_9|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"180020": {
"content": "<|extra_id_10|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|fim_prefix|>",
"<|fim_middle|>",
"<|fim_suffix|>",
"|||PHONE_NUMBER|||",
"|||EMAIL_ADDRESS|||",
"|||IP_ADDRESS|||",
"<|im_start|>",
"<|im_end|>",
"<|extra_id_0|>",
"<|extra_id_1|>",
"<|extra_id_2|>",
"<|extra_id_3|>",
"<|extra_id_4|>",
"<|extra_id_5|>",
"<|extra_id_6|>",
"<|extra_id_7|>",
"<|extra_id_8|>",
"<|extra_id_9|>",
"<|extra_id_10|>"
],
"bos_token": "<|endoftext|>",
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 8192,
"pad_token": "<|pad|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}