Upload 2 files
Browse files- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
|
3 |
+
size 2001107
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"auto_map": {
|
5 |
+
"AutoTokenizer": [
|
6 |
+
"tokenization_baichuan.BaichuanTokenizer",
|
7 |
+
null
|
8 |
+
]
|
9 |
+
},
|
10 |
+
"bos_token": {
|
11 |
+
"__type": "AddedToken",
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"clean_up_tokenization_spaces": false,
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": true
|
26 |
+
},
|
27 |
+
"model_max_length": 4096,
|
28 |
+
"pad_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": true
|
35 |
+
},
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"split_special_tokens": false,
|
39 |
+
"tokenizer_class": "BaichuanTokenizer",
|
40 |
+
"unk_token": {
|
41 |
+
"__type": "AddedToken",
|
42 |
+
"content": "<unk>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": true
|
47 |
+
},
|
48 |
+
"use_fast": false
|
49 |
+
}
|