first commit

This commit is contained in:
Jintao Huang
2023-10-20 23:38:22 +08:00
parent 692b1db444
commit f9199225e8
12 changed files with 93924 additions and 43 deletions

35
tokenizer_config.json Executable file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}