socially-good-lm / tokenizer_config.json
agi-css's picture
Release v1
c677efc
raw
history blame
795 Bytes
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 192,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"special_tokens_map_file": "/media/css_models/new_v8/special_tokens_map.json",
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}