TinyStories-3M-val-Hebrew / tokenizer_config.json
Norod78's picture
TinyStories-3M-val-Hebrew
cbeb2d3
raw
history blame
486 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|pad|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unknown_token": "<|unknown|>"
}