MathGenie-InterLM-20B / tokenizer_config.json
陆子睦
First model version
05f4178
{
"add_bos_token": true,
"add_eos_token": false,
"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
},
"92544": {
"content": "<|text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92545": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92546": {
"content": "<|endofblock|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92547": {
"content": "<|endofmessage|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92548": {
"content": "<|code|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92549": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92550": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"92551": {
"content": "<|execution|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|text|>",
"<|assistant|>",
"<|endofblock|>",
"<|endofmessage|>",
"<|code|>",
"<|system|>",
"<|user|>",
"<|execution|>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_internlm2.InternLM2Tokenizer",
"tokenization_internlm2_fast.InternLM2TokenizerFast"
]
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"decode_with_prefix_space": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": null,
"tokenizer_class": "InternLM2Tokenizer",
"unk_token": "<unk>"
}