smol_llama-101M-GQA-python / tokenizer_config.json
pszemraj's picture
Upload tokenizer
15280a6
raw
history blame
No virus
16.3 kB
{
"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
},
"32000": {
"content": "**kwargs",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32001": {
"content": "@abstractmethod",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32002": {
"content": "@classmethod",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32003": {
"content": "@property",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32004": {
"content": "@staticmethod",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32005": {
"content": "__all__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32006": {
"content": "__call__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32007": {
"content": "__class__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32008": {
"content": "__contains__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32009": {
"content": "__delitem__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32010": {
"content": "__del__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32011": {
"content": "__dict__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32012": {
"content": "__doc__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32013": {
"content": "__file__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32014": {
"content": "__future__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32015": {
"content": "__getitem__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32016": {
"content": "__init__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32017": {
"content": "__len__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32018": {
"content": "__main__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32019": {
"content": "__name__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32020": {
"content": "__package__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32021": {
"content": "__props__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32022": {
"content": "__repr__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32023": {
"content": "__self__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32024": {
"content": "__setitem__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32025": {
"content": "__str__",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32026": {
"content": "*args",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": true,
"special": false
},
"32027": {
"content": "GraphQL",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32028": {
"content": "JWT",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32029": {
"content": "OAuth",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32030": {
"content": "DELETE",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32031": {
"content": "JOIN",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32032": {
"content": "gRPC",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32033": {
"content": "rtype",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32034": {
"content": "TODO",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32035": {
"content": "Notes",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32036": {
"content": ">>> ",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32037": {
"content": "Raises",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32038": {
"content": "AttributeError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32039": {
"content": "Callable",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32040": {
"content": "ImportError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32041": {
"content": "KeyError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32042": {
"content": "NotImplementedError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32043": {
"content": "README",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32044": {
"content": "RuntimeError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32045": {
"content": "Tuple",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32046": {
"content": "TypeError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32047": {
"content": "ValueError",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32048": {
"content": "asyncio",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32049": {
"content": "dtype",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32050": {
"content": "finally",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32051": {
"content": "cuda",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32052": {
"content": "functools",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32053": {
"content": "getattr",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32054": {
"content": "getter",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32055": {
"content": "hasattr",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32056": {
"content": "itertools",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32057": {
"content": "jsii",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32058": {
"content": "pathlib",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32059": {
"content": "plt",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32060": {
"content": "pulumi",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32061": {
"content": "pickle",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32062": {
"content": "setter",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32063": {
"content": "shutil",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32064": {
"content": "sklearn",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32065": {
"content": "stderr",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32066": {
"content": "torch",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32067": {
"content": "locals()",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32068": {
"content": "globals()",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32069": {
"content": "yield",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32070": {
"content": "<0x0A><0x0A>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32071": {
"content": "<0x0A><0x0A><0x0A>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32072": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32073": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32074": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32075": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32076": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32077": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32078": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32079": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32080": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32081": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"use_default_system_prompt": true
}