xgen-7b-tuned-alpaca / tokenizer_config.json
dsmonk's picture
Training in progress, epoch 0
6f194a3
raw
history blame
489 Bytes
{
"add_eos_token": false,
"add_special_tokens": true,
"auto_map": {
"AutoTokenizer": [
"Salesforce/xgen-7b-8k-base--tokenization_xgen.XgenTokenizer",
null
]
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 8192,
"pad_token": null,
"tokenizer_class": "XgenTokenizer"
}