elm-v0.1 / elm-1.0_news_summarization /tokenizer_config.json
chinnadhurai sankar
initial commit
582bf94
raw
history blame contribute delete
687 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 1024,
"pad_token": "[PAD]",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}