bueble-lm-2b / checkpoint-1400 /tokenizer_config.json
pdelobelle's picture
Training in progress, step 1400, checkpoint
74c6671 verified
raw
history blame
6.95 kB
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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": "▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"5": {
"content": "▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"6": {
"content": "▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"7": {
"content": "▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"8": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"9": {
"content": "--",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"10": {
"content": "----",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"11": {
"content": "-----",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"12": {
"content": "--------",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"13": {
"content": "----------------",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"14": {
"content": "++",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"15": {
"content": "/**",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"16": {
"content": "***",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"17": {
"content": "****",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"18": {
"content": "******",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"19": {
"content": "********",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"20": {
"content": "**/",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"21": {
"content": "##",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"22": {
"content": "###",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"23": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"24": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"25": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"26": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"27": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"28": {
"content": "▁—",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"29": {
"content": "β–β€œ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"30": {
"content": "β€œ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"31": {
"content": "”",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32": {
"content": "’",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"33": {
"content": "β€”",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"34": {
"content": "{",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"35": {
"content": "}\"",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"36": {
"content": "{\"",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"37": {
"content": "}",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}