titler / tokenizer_config.json
Cyronius's picture
v1.5: LMSYS-Chat-1M data expansion, collapse fix, quant benchmark
53b2c46 verified
Raw
History Blame Contribute Delete
789 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"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": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 512,
"pad_token": "<pad>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}