ablation-exp-fw-base_filtering-350BT / tokenizer_config.json
guipenedo's picture
guipenedo HF staff
Upload tokenizer
6b6835c verified
raw
history blame contribute delete
444 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}