Upload tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer.json +2 -11
- tokenizer.model +3 -0
- tokenizer_config.json +6 -4
special_tokens_map.json
CHANGED
@@ -2,14 +2,14 @@
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
5 |
-
"normalized":
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
@@ -17,7 +17,7 @@
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
20 |
-
"normalized":
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
|
|
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 |
},
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
tokenizer.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
21 |
-
"normalized":
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
@@ -27,17 +27,8 @@
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
-
"normalized":
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 32000,
|
35 |
-
"content": "<pad>",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"special": false
|
41 |
}
|
42 |
],
|
43 |
"normalizer": {
|
|
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"__type": "AddedToken",
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
@@ -12,21 +12,23 @@
|
|
12 |
"__type": "AddedToken",
|
13 |
"content": "</s>",
|
14 |
"lstrip": false,
|
15 |
-
"normalized":
|
16 |
"rstrip": false,
|
17 |
"single_word": false
|
18 |
},
|
19 |
"legacy": false,
|
20 |
"model_max_length": 1000000000000000019884624838656,
|
21 |
"pad_token": null,
|
|
|
22 |
"sp_model_kwargs": {},
|
23 |
"tokenizer_class": "LlamaTokenizer",
|
24 |
"unk_token": {
|
25 |
"__type": "AddedToken",
|
26 |
"content": "<unk>",
|
27 |
"lstrip": false,
|
28 |
-
"normalized":
|
29 |
"rstrip": false,
|
30 |
"single_word": false
|
31 |
-
}
|
|
|
32 |
}
|
|
|
3 |
"__type": "AddedToken",
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
|
|
12 |
"__type": "AddedToken",
|
13 |
"content": "</s>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false
|
18 |
},
|
19 |
"legacy": false,
|
20 |
"model_max_length": 1000000000000000019884624838656,
|
21 |
"pad_token": null,
|
22 |
+
"padding_side": "right",
|
23 |
"sp_model_kwargs": {},
|
24 |
"tokenizer_class": "LlamaTokenizer",
|
25 |
"unk_token": {
|
26 |
"__type": "AddedToken",
|
27 |
"content": "<unk>",
|
28 |
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
"rstrip": false,
|
31 |
"single_word": false
|
32 |
+
},
|
33 |
+
"use_default_system_prompt": true
|
34 |
}
|