Tanuki-8B-vision / tokenizer_config.json
kanhatakeyama's picture
Duplicate from team-hatakeyama-phase2/Tanuki-8B-vision-v4-checkpoint-18000
3e35b51 verified
raw
history blame
2.48 kB
{
"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
},
"3": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<EOD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<MASK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<llm-code>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "</llm-code>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<llm-code-output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"12": {
"content": "</llm-code-output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<EOD>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<CLS>",
"eos_token": "</s>",
"extra_ids": 0,
"mask_token": "<MASK>",
"model_max_length": 8192,
"pad_token": "<unk>",
"padding_side": "right",
"sep_token": "<SEP>",
"sp_model_kwargs": {},
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}