tamil-tiny-stories / tokenizer_config.json
senthil090's picture
initial model 10000 epoch
b99ff82 verified
{
"added_tokens_decoder": {
"447": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"448": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"449": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"450": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_tamil_tiny_stories.TamilTinyStoriesTokenizer",
null
]
},
"backend": "custom",
"bos_token": "<bos>",
"eos_token": "<eos>",
"model_max_length": 128,
"pad_token": "<pad>",
"padding_side": "left",
"tokenizer_class": "TamilTinyStoriesTokenizer",
"unk_token": "<unk>"
}