chrisyuan45
commited on
Commit
•
cdd0b1a
1
Parent(s):
1389f12
Upload 4 files
Browse files- special_tokens_map.json +21 -4
- tokenizer_config.json +23 -40
special_tokens_map.json
CHANGED
@@ -1,6 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -1,52 +1,35 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
"special": false
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": false
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false,
|
27 |
-
"special": false
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<PAD>",
|
31 |
-
"lstrip": true,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": true,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
}
|
37 |
},
|
38 |
-
"additional_special_tokens": [],
|
39 |
-
"bos_token": "<s>",
|
40 |
"clean_up_tokenization_spaces": false,
|
41 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
"legacy": false,
|
43 |
"model_max_length": 1000000000000000019884624838656,
|
44 |
"pad_token": null,
|
45 |
"padding_side": "right",
|
46 |
"sp_model_kwargs": {},
|
47 |
-
"spaces_between_special_tokens": false,
|
48 |
"tokenizer_class": "LlamaTokenizer",
|
49 |
-
"
|
50 |
-
|
51 |
-
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
},
|
|
|
|
|
12 |
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
"legacy": false,
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
24 |
"padding_side": "right",
|
25 |
"sp_model_kwargs": {},
|
|
|
26 |
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
}
|