dododododo
commited on
Commit
•
2ba9cca
1
Parent(s):
73ad007
Upload Chinese_tiny_llm-en_105k/tokenizer_config.json with huggingface_hub
Browse files
Chinese_tiny_llm-en_105k/tokenizer_config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": true,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": true,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"125696": {
|
30 |
+
"content": "<|EOD|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"125697": {
|
38 |
+
"content": "<|MASK|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"125698": {
|
46 |
+
"content": "<|PAD|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<|EOD|>",
|
56 |
+
"<|MASK|>",
|
57 |
+
"<|PAD|>"
|
58 |
+
],
|
59 |
+
"auto_map": {
|
60 |
+
"AutoTokenizer": [
|
61 |
+
"tokenization_baichuan.BaichuanTokenizer",
|
62 |
+
null
|
63 |
+
]
|
64 |
+
},
|
65 |
+
"bos_token": "<s>",
|
66 |
+
"clean_up_tokenization_spaces": false,
|
67 |
+
"eos_token": "</s>",
|
68 |
+
"model_max_length": 4096,
|
69 |
+
"pad_token": "<unk>",
|
70 |
+
"padding_side": "right",
|
71 |
+
"sp_model_kwargs": {},
|
72 |
+
"split_special_tokens": false,
|
73 |
+
"tokenizer_class": "BaichuanTokenizer",
|
74 |
+
"unk_token": "<unk>",
|
75 |
+
"use_fast": false
|
76 |
+
}
|