markoarnauto
commited on
Commit
•
6f32845
1
Parent(s):
cfa3f9d
tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +2109 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e54b0a797c9ead3c0488bfbf18ae5558d5361ea9732ad263d173b02380910f73
|
3 |
+
size 15782902
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254
|
3 |
+
size 2408875
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"3": {
|
31 |
+
"content": "<|im_start|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"4": {
|
39 |
+
"content": "<|im_end|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"5": {
|
47 |
+
"content": "<extra_id_0>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"6": {
|
55 |
+
"content": "<extra_id_1>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"7": {
|
63 |
+
"content": "<extra_id_2>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"8": {
|
71 |
+
"content": "<extra_id_3>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"9": {
|
79 |
+
"content": "<extra_id_4>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"10": {
|
87 |
+
"content": "<extra_id_5>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"11": {
|
95 |
+
"content": "<extra_id_6>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"12": {
|
103 |
+
"content": "<extra_id_7>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"13": {
|
111 |
+
"content": "<extra_id_8>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"14": {
|
119 |
+
"content": "<extra_id_9>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"15": {
|
127 |
+
"content": "<extra_id_10>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"16": {
|
135 |
+
"content": "<extra_id_11>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"17": {
|
143 |
+
"content": "<extra_id_12>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"18": {
|
151 |
+
"content": "<extra_id_13>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"19": {
|
159 |
+
"content": "<extra_id_14>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"20": {
|
167 |
+
"content": "<extra_id_15>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"21": {
|
175 |
+
"content": "<extra_id_16>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"22": {
|
183 |
+
"content": "<extra_id_17>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"23": {
|
191 |
+
"content": "<extra_id_18>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"24": {
|
199 |
+
"content": "<extra_id_19>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"25": {
|
207 |
+
"content": "<extra_id_20>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"26": {
|
215 |
+
"content": "<extra_id_21>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"27": {
|
223 |
+
"content": "<extra_id_22>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
+
},
|
230 |
+
"28": {
|
231 |
+
"content": "<extra_id_23>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": false
|
237 |
+
},
|
238 |
+
"29": {
|
239 |
+
"content": "<extra_id_24>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": false
|
245 |
+
},
|
246 |
+
"30": {
|
247 |
+
"content": "<extra_id_25>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
"31": {
|
255 |
+
"content": "<extra_id_26>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": false
|
261 |
+
},
|
262 |
+
"32": {
|
263 |
+
"content": "<extra_id_27>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": false
|
269 |
+
},
|
270 |
+
"33": {
|
271 |
+
"content": "<extra_id_28>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": false
|
277 |
+
},
|
278 |
+
"34": {
|
279 |
+
"content": "<extra_id_29>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": false
|
285 |
+
},
|
286 |
+
"35": {
|
287 |
+
"content": "<extra_id_30>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
"36": {
|
295 |
+
"content": "<extra_id_31>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": false
|
301 |
+
},
|
302 |
+
"37": {
|
303 |
+
"content": "<extra_id_32>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": false
|
309 |
+
},
|
310 |
+
"38": {
|
311 |
+
"content": "<extra_id_33>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": false
|
317 |
+
},
|
318 |
+
"39": {
|
319 |
+
"content": "<extra_id_34>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": false
|
325 |
+
},
|
326 |
+
"40": {
|
327 |
+
"content": "<extra_id_35>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": false
|
333 |
+
},
|
334 |
+
"41": {
|
335 |
+
"content": "<extra_id_36>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": false
|
341 |
+
},
|
342 |
+
"42": {
|
343 |
+
"content": "<extra_id_37>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": false
|
349 |
+
},
|
350 |
+
"43": {
|
351 |
+
"content": "<extra_id_38>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": false
|
357 |
+
},
|
358 |
+
"44": {
|
359 |
+
"content": "<extra_id_39>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": false
|
365 |
+
},
|
366 |
+
"45": {
|
367 |
+
"content": "<extra_id_40>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": false
|
373 |
+
},
|
374 |
+
"46": {
|
375 |
+
"content": "<extra_id_41>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": false
|
381 |
+
},
|
382 |
+
"47": {
|
383 |
+
"content": "<extra_id_42>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": false
|
389 |
+
},
|
390 |
+
"48": {
|
391 |
+
"content": "<extra_id_43>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": false
|
397 |
+
},
|
398 |
+
"49": {
|
399 |
+
"content": "<extra_id_44>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": false
|
405 |
+
},
|
406 |
+
"50": {
|
407 |
+
"content": "<extra_id_45>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": false
|
413 |
+
},
|
414 |
+
"51": {
|
415 |
+
"content": "<extra_id_46>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": false
|
421 |
+
},
|
422 |
+
"52": {
|
423 |
+
"content": "<extra_id_47>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": false
|
429 |
+
},
|
430 |
+
"53": {
|
431 |
+
"content": "<extra_id_48>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": false
|
437 |
+
},
|
438 |
+
"54": {
|
439 |
+
"content": "<extra_id_49>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": false
|
445 |
+
},
|
446 |
+
"55": {
|
447 |
+
"content": "<extra_id_50>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": false
|
453 |
+
},
|
454 |
+
"56": {
|
455 |
+
"content": "<extra_id_51>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": false
|
461 |
+
},
|
462 |
+
"57": {
|
463 |
+
"content": "<extra_id_52>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": false
|
469 |
+
},
|
470 |
+
"58": {
|
471 |
+
"content": "<extra_id_53>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": false
|
477 |
+
},
|
478 |
+
"59": {
|
479 |
+
"content": "<extra_id_54>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": false
|
485 |
+
},
|
486 |
+
"60": {
|
487 |
+
"content": "<extra_id_55>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": false
|
493 |
+
},
|
494 |
+
"61": {
|
495 |
+
"content": "<extra_id_56>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": false
|
501 |
+
},
|
502 |
+
"62": {
|
503 |
+
"content": "<extra_id_57>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": false
|
509 |
+
},
|
510 |
+
"63": {
|
511 |
+
"content": "<extra_id_58>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": false
|
517 |
+
},
|
518 |
+
"64": {
|
519 |
+
"content": "<extra_id_59>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": false
|
525 |
+
},
|
526 |
+
"65": {
|
527 |
+
"content": "<extra_id_60>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": false
|
533 |
+
},
|
534 |
+
"66": {
|
535 |
+
"content": "<extra_id_61>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": false
|
541 |
+
},
|
542 |
+
"67": {
|
543 |
+
"content": "<extra_id_62>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": false
|
549 |
+
},
|
550 |
+
"68": {
|
551 |
+
"content": "<extra_id_63>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": false
|
557 |
+
},
|
558 |
+
"69": {
|
559 |
+
"content": "<extra_id_64>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": false
|
565 |
+
},
|
566 |
+
"70": {
|
567 |
+
"content": "<extra_id_65>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": false
|
573 |
+
},
|
574 |
+
"71": {
|
575 |
+
"content": "<extra_id_66>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": false
|
581 |
+
},
|
582 |
+
"72": {
|
583 |
+
"content": "<extra_id_67>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": false
|
589 |
+
},
|
590 |
+
"73": {
|
591 |
+
"content": "<extra_id_68>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": false
|
597 |
+
},
|
598 |
+
"74": {
|
599 |
+
"content": "<extra_id_69>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": false
|
605 |
+
},
|
606 |
+
"75": {
|
607 |
+
"content": "<extra_id_70>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": false
|
613 |
+
},
|
614 |
+
"76": {
|
615 |
+
"content": "<extra_id_71>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": false
|
621 |
+
},
|
622 |
+
"77": {
|
623 |
+
"content": "<extra_id_72>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": false
|
629 |
+
},
|
630 |
+
"78": {
|
631 |
+
"content": "<extra_id_73>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": false
|
637 |
+
},
|
638 |
+
"79": {
|
639 |
+
"content": "<extra_id_74>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": false
|
645 |
+
},
|
646 |
+
"80": {
|
647 |
+
"content": "<extra_id_75>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": false
|
653 |
+
},
|
654 |
+
"81": {
|
655 |
+
"content": "<extra_id_76>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": false
|
661 |
+
},
|
662 |
+
"82": {
|
663 |
+
"content": "<extra_id_77>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": false
|
669 |
+
},
|
670 |
+
"83": {
|
671 |
+
"content": "<extra_id_78>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": false
|
677 |
+
},
|
678 |
+
"84": {
|
679 |
+
"content": "<extra_id_79>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": false
|
685 |
+
},
|
686 |
+
"85": {
|
687 |
+
"content": "<extra_id_80>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": false
|
693 |
+
},
|
694 |
+
"86": {
|
695 |
+
"content": "<extra_id_81>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": false
|
701 |
+
},
|
702 |
+
"87": {
|
703 |
+
"content": "<extra_id_82>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": false
|
709 |
+
},
|
710 |
+
"88": {
|
711 |
+
"content": "<extra_id_83>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": false
|
717 |
+
},
|
718 |
+
"89": {
|
719 |
+
"content": "<extra_id_84>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": false
|
725 |
+
},
|
726 |
+
"90": {
|
727 |
+
"content": "<extra_id_85>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": false
|
733 |
+
},
|
734 |
+
"91": {
|
735 |
+
"content": "<extra_id_86>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": false
|
741 |
+
},
|
742 |
+
"92": {
|
743 |
+
"content": "<extra_id_87>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": false
|
749 |
+
},
|
750 |
+
"93": {
|
751 |
+
"content": "<extra_id_88>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": false
|
757 |
+
},
|
758 |
+
"94": {
|
759 |
+
"content": "<extra_id_89>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": false
|
765 |
+
},
|
766 |
+
"95": {
|
767 |
+
"content": "<extra_id_90>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": false
|
773 |
+
},
|
774 |
+
"96": {
|
775 |
+
"content": "<extra_id_91>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": false
|
781 |
+
},
|
782 |
+
"97": {
|
783 |
+
"content": "<extra_id_92>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": false
|
789 |
+
},
|
790 |
+
"98": {
|
791 |
+
"content": "<extra_id_93>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": false
|
797 |
+
},
|
798 |
+
"99": {
|
799 |
+
"content": "<extra_id_94>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": false
|
805 |
+
},
|
806 |
+
"100": {
|
807 |
+
"content": "<extra_id_95>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": false
|
813 |
+
},
|
814 |
+
"101": {
|
815 |
+
"content": "<extra_id_96>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": false
|
821 |
+
},
|
822 |
+
"102": {
|
823 |
+
"content": "<extra_id_97>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": false
|
829 |
+
},
|
830 |
+
"103": {
|
831 |
+
"content": "<extra_id_98>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": false
|
837 |
+
},
|
838 |
+
"104": {
|
839 |
+
"content": "<extra_id_99>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": false
|
845 |
+
},
|
846 |
+
"105": {
|
847 |
+
"content": "<extra_id_100>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": false
|
853 |
+
},
|
854 |
+
"106": {
|
855 |
+
"content": "<extra_id_101>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": false
|
861 |
+
},
|
862 |
+
"107": {
|
863 |
+
"content": "<extra_id_102>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": false
|
869 |
+
},
|
870 |
+
"108": {
|
871 |
+
"content": "<extra_id_103>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": false
|
877 |
+
},
|
878 |
+
"109": {
|
879 |
+
"content": "<extra_id_104>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": false
|
885 |
+
},
|
886 |
+
"110": {
|
887 |
+
"content": "<extra_id_105>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": false
|
893 |
+
},
|
894 |
+
"111": {
|
895 |
+
"content": "<extra_id_106>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": false
|
901 |
+
},
|
902 |
+
"112": {
|
903 |
+
"content": "<extra_id_107>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": false
|
909 |
+
},
|
910 |
+
"113": {
|
911 |
+
"content": "<extra_id_108>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": false
|
917 |
+
},
|
918 |
+
"114": {
|
919 |
+
"content": "<extra_id_109>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": false
|
925 |
+
},
|
926 |
+
"115": {
|
927 |
+
"content": "<extra_id_110>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": false
|
933 |
+
},
|
934 |
+
"116": {
|
935 |
+
"content": "<extra_id_111>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": false
|
941 |
+
},
|
942 |
+
"117": {
|
943 |
+
"content": "<extra_id_112>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": false
|
949 |
+
},
|
950 |
+
"118": {
|
951 |
+
"content": "<extra_id_113>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": false
|
957 |
+
},
|
958 |
+
"119": {
|
959 |
+
"content": "<extra_id_114>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": false
|
965 |
+
},
|
966 |
+
"120": {
|
967 |
+
"content": "<extra_id_115>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": false
|
973 |
+
},
|
974 |
+
"121": {
|
975 |
+
"content": "<extra_id_116>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": false
|
981 |
+
},
|
982 |
+
"122": {
|
983 |
+
"content": "<extra_id_117>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": false
|
989 |
+
},
|
990 |
+
"123": {
|
991 |
+
"content": "<extra_id_118>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": false
|
997 |
+
},
|
998 |
+
"124": {
|
999 |
+
"content": "<extra_id_119>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": false
|
1005 |
+
},
|
1006 |
+
"125": {
|
1007 |
+
"content": "<extra_id_120>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": false
|
1013 |
+
},
|
1014 |
+
"126": {
|
1015 |
+
"content": "<extra_id_121>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": false
|
1021 |
+
},
|
1022 |
+
"127": {
|
1023 |
+
"content": "<extra_id_122>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": false
|
1029 |
+
},
|
1030 |
+
"128": {
|
1031 |
+
"content": "<extra_id_123>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": false
|
1037 |
+
},
|
1038 |
+
"129": {
|
1039 |
+
"content": "<extra_id_124>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": false
|
1045 |
+
},
|
1046 |
+
"130": {
|
1047 |
+
"content": "<extra_id_125>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": false
|
1053 |
+
},
|
1054 |
+
"131": {
|
1055 |
+
"content": "<extra_id_126>",
|
1056 |
+
"lstrip": false,
|
1057 |
+
"normalized": false,
|
1058 |
+
"rstrip": false,
|
1059 |
+
"single_word": false,
|
1060 |
+
"special": false
|
1061 |
+
},
|
1062 |
+
"132": {
|
1063 |
+
"content": "<extra_id_127>",
|
1064 |
+
"lstrip": false,
|
1065 |
+
"normalized": false,
|
1066 |
+
"rstrip": false,
|
1067 |
+
"single_word": false,
|
1068 |
+
"special": false
|
1069 |
+
},
|
1070 |
+
"133": {
|
1071 |
+
"content": "<extra_id_128>",
|
1072 |
+
"lstrip": false,
|
1073 |
+
"normalized": false,
|
1074 |
+
"rstrip": false,
|
1075 |
+
"single_word": false,
|
1076 |
+
"special": false
|
1077 |
+
},
|
1078 |
+
"134": {
|
1079 |
+
"content": "<extra_id_129>",
|
1080 |
+
"lstrip": false,
|
1081 |
+
"normalized": false,
|
1082 |
+
"rstrip": false,
|
1083 |
+
"single_word": false,
|
1084 |
+
"special": false
|
1085 |
+
},
|
1086 |
+
"135": {
|
1087 |
+
"content": "<extra_id_130>",
|
1088 |
+
"lstrip": false,
|
1089 |
+
"normalized": false,
|
1090 |
+
"rstrip": false,
|
1091 |
+
"single_word": false,
|
1092 |
+
"special": false
|
1093 |
+
},
|
1094 |
+
"136": {
|
1095 |
+
"content": "<extra_id_131>",
|
1096 |
+
"lstrip": false,
|
1097 |
+
"normalized": false,
|
1098 |
+
"rstrip": false,
|
1099 |
+
"single_word": false,
|
1100 |
+
"special": false
|
1101 |
+
},
|
1102 |
+
"137": {
|
1103 |
+
"content": "<extra_id_132>",
|
1104 |
+
"lstrip": false,
|
1105 |
+
"normalized": false,
|
1106 |
+
"rstrip": false,
|
1107 |
+
"single_word": false,
|
1108 |
+
"special": false
|
1109 |
+
},
|
1110 |
+
"138": {
|
1111 |
+
"content": "<extra_id_133>",
|
1112 |
+
"lstrip": false,
|
1113 |
+
"normalized": false,
|
1114 |
+
"rstrip": false,
|
1115 |
+
"single_word": false,
|
1116 |
+
"special": false
|
1117 |
+
},
|
1118 |
+
"139": {
|
1119 |
+
"content": "<extra_id_134>",
|
1120 |
+
"lstrip": false,
|
1121 |
+
"normalized": false,
|
1122 |
+
"rstrip": false,
|
1123 |
+
"single_word": false,
|
1124 |
+
"special": false
|
1125 |
+
},
|
1126 |
+
"140": {
|
1127 |
+
"content": "<extra_id_135>",
|
1128 |
+
"lstrip": false,
|
1129 |
+
"normalized": false,
|
1130 |
+
"rstrip": false,
|
1131 |
+
"single_word": false,
|
1132 |
+
"special": false
|
1133 |
+
},
|
1134 |
+
"141": {
|
1135 |
+
"content": "<extra_id_136>",
|
1136 |
+
"lstrip": false,
|
1137 |
+
"normalized": false,
|
1138 |
+
"rstrip": false,
|
1139 |
+
"single_word": false,
|
1140 |
+
"special": false
|
1141 |
+
},
|
1142 |
+
"142": {
|
1143 |
+
"content": "<extra_id_137>",
|
1144 |
+
"lstrip": false,
|
1145 |
+
"normalized": false,
|
1146 |
+
"rstrip": false,
|
1147 |
+
"single_word": false,
|
1148 |
+
"special": false
|
1149 |
+
},
|
1150 |
+
"143": {
|
1151 |
+
"content": "<extra_id_138>",
|
1152 |
+
"lstrip": false,
|
1153 |
+
"normalized": false,
|
1154 |
+
"rstrip": false,
|
1155 |
+
"single_word": false,
|
1156 |
+
"special": false
|
1157 |
+
},
|
1158 |
+
"144": {
|
1159 |
+
"content": "<extra_id_139>",
|
1160 |
+
"lstrip": false,
|
1161 |
+
"normalized": false,
|
1162 |
+
"rstrip": false,
|
1163 |
+
"single_word": false,
|
1164 |
+
"special": false
|
1165 |
+
},
|
1166 |
+
"145": {
|
1167 |
+
"content": "<extra_id_140>",
|
1168 |
+
"lstrip": false,
|
1169 |
+
"normalized": false,
|
1170 |
+
"rstrip": false,
|
1171 |
+
"single_word": false,
|
1172 |
+
"special": false
|
1173 |
+
},
|
1174 |
+
"146": {
|
1175 |
+
"content": "<extra_id_141>",
|
1176 |
+
"lstrip": false,
|
1177 |
+
"normalized": false,
|
1178 |
+
"rstrip": false,
|
1179 |
+
"single_word": false,
|
1180 |
+
"special": false
|
1181 |
+
},
|
1182 |
+
"147": {
|
1183 |
+
"content": "<extra_id_142>",
|
1184 |
+
"lstrip": false,
|
1185 |
+
"normalized": false,
|
1186 |
+
"rstrip": false,
|
1187 |
+
"single_word": false,
|
1188 |
+
"special": false
|
1189 |
+
},
|
1190 |
+
"148": {
|
1191 |
+
"content": "<extra_id_143>",
|
1192 |
+
"lstrip": false,
|
1193 |
+
"normalized": false,
|
1194 |
+
"rstrip": false,
|
1195 |
+
"single_word": false,
|
1196 |
+
"special": false
|
1197 |
+
},
|
1198 |
+
"149": {
|
1199 |
+
"content": "<extra_id_144>",
|
1200 |
+
"lstrip": false,
|
1201 |
+
"normalized": false,
|
1202 |
+
"rstrip": false,
|
1203 |
+
"single_word": false,
|
1204 |
+
"special": false
|
1205 |
+
},
|
1206 |
+
"150": {
|
1207 |
+
"content": "<extra_id_145>",
|
1208 |
+
"lstrip": false,
|
1209 |
+
"normalized": false,
|
1210 |
+
"rstrip": false,
|
1211 |
+
"single_word": false,
|
1212 |
+
"special": false
|
1213 |
+
},
|
1214 |
+
"151": {
|
1215 |
+
"content": "<extra_id_146>",
|
1216 |
+
"lstrip": false,
|
1217 |
+
"normalized": false,
|
1218 |
+
"rstrip": false,
|
1219 |
+
"single_word": false,
|
1220 |
+
"special": false
|
1221 |
+
},
|
1222 |
+
"152": {
|
1223 |
+
"content": "<extra_id_147>",
|
1224 |
+
"lstrip": false,
|
1225 |
+
"normalized": false,
|
1226 |
+
"rstrip": false,
|
1227 |
+
"single_word": false,
|
1228 |
+
"special": false
|
1229 |
+
},
|
1230 |
+
"153": {
|
1231 |
+
"content": "<extra_id_148>",
|
1232 |
+
"lstrip": false,
|
1233 |
+
"normalized": false,
|
1234 |
+
"rstrip": false,
|
1235 |
+
"single_word": false,
|
1236 |
+
"special": false
|
1237 |
+
},
|
1238 |
+
"154": {
|
1239 |
+
"content": "<extra_id_149>",
|
1240 |
+
"lstrip": false,
|
1241 |
+
"normalized": false,
|
1242 |
+
"rstrip": false,
|
1243 |
+
"single_word": false,
|
1244 |
+
"special": false
|
1245 |
+
},
|
1246 |
+
"155": {
|
1247 |
+
"content": "<extra_id_150>",
|
1248 |
+
"lstrip": false,
|
1249 |
+
"normalized": false,
|
1250 |
+
"rstrip": false,
|
1251 |
+
"single_word": false,
|
1252 |
+
"special": false
|
1253 |
+
},
|
1254 |
+
"156": {
|
1255 |
+
"content": "<extra_id_151>",
|
1256 |
+
"lstrip": false,
|
1257 |
+
"normalized": false,
|
1258 |
+
"rstrip": false,
|
1259 |
+
"single_word": false,
|
1260 |
+
"special": false
|
1261 |
+
},
|
1262 |
+
"157": {
|
1263 |
+
"content": "<extra_id_152>",
|
1264 |
+
"lstrip": false,
|
1265 |
+
"normalized": false,
|
1266 |
+
"rstrip": false,
|
1267 |
+
"single_word": false,
|
1268 |
+
"special": false
|
1269 |
+
},
|
1270 |
+
"158": {
|
1271 |
+
"content": "<extra_id_153>",
|
1272 |
+
"lstrip": false,
|
1273 |
+
"normalized": false,
|
1274 |
+
"rstrip": false,
|
1275 |
+
"single_word": false,
|
1276 |
+
"special": false
|
1277 |
+
},
|
1278 |
+
"159": {
|
1279 |
+
"content": "<extra_id_154>",
|
1280 |
+
"lstrip": false,
|
1281 |
+
"normalized": false,
|
1282 |
+
"rstrip": false,
|
1283 |
+
"single_word": false,
|
1284 |
+
"special": false
|
1285 |
+
},
|
1286 |
+
"160": {
|
1287 |
+
"content": "<extra_id_155>",
|
1288 |
+
"lstrip": false,
|
1289 |
+
"normalized": false,
|
1290 |
+
"rstrip": false,
|
1291 |
+
"single_word": false,
|
1292 |
+
"special": false
|
1293 |
+
},
|
1294 |
+
"161": {
|
1295 |
+
"content": "<extra_id_156>",
|
1296 |
+
"lstrip": false,
|
1297 |
+
"normalized": false,
|
1298 |
+
"rstrip": false,
|
1299 |
+
"single_word": false,
|
1300 |
+
"special": false
|
1301 |
+
},
|
1302 |
+
"162": {
|
1303 |
+
"content": "<extra_id_157>",
|
1304 |
+
"lstrip": false,
|
1305 |
+
"normalized": false,
|
1306 |
+
"rstrip": false,
|
1307 |
+
"single_word": false,
|
1308 |
+
"special": false
|
1309 |
+
},
|
1310 |
+
"163": {
|
1311 |
+
"content": "<extra_id_158>",
|
1312 |
+
"lstrip": false,
|
1313 |
+
"normalized": false,
|
1314 |
+
"rstrip": false,
|
1315 |
+
"single_word": false,
|
1316 |
+
"special": false
|
1317 |
+
},
|
1318 |
+
"164": {
|
1319 |
+
"content": "<extra_id_159>",
|
1320 |
+
"lstrip": false,
|
1321 |
+
"normalized": false,
|
1322 |
+
"rstrip": false,
|
1323 |
+
"single_word": false,
|
1324 |
+
"special": false
|
1325 |
+
},
|
1326 |
+
"165": {
|
1327 |
+
"content": "<extra_id_160>",
|
1328 |
+
"lstrip": false,
|
1329 |
+
"normalized": false,
|
1330 |
+
"rstrip": false,
|
1331 |
+
"single_word": false,
|
1332 |
+
"special": false
|
1333 |
+
},
|
1334 |
+
"166": {
|
1335 |
+
"content": "<extra_id_161>",
|
1336 |
+
"lstrip": false,
|
1337 |
+
"normalized": false,
|
1338 |
+
"rstrip": false,
|
1339 |
+
"single_word": false,
|
1340 |
+
"special": false
|
1341 |
+
},
|
1342 |
+
"167": {
|
1343 |
+
"content": "<extra_id_162>",
|
1344 |
+
"lstrip": false,
|
1345 |
+
"normalized": false,
|
1346 |
+
"rstrip": false,
|
1347 |
+
"single_word": false,
|
1348 |
+
"special": false
|
1349 |
+
},
|
1350 |
+
"168": {
|
1351 |
+
"content": "<extra_id_163>",
|
1352 |
+
"lstrip": false,
|
1353 |
+
"normalized": false,
|
1354 |
+
"rstrip": false,
|
1355 |
+
"single_word": false,
|
1356 |
+
"special": false
|
1357 |
+
},
|
1358 |
+
"169": {
|
1359 |
+
"content": "<extra_id_164>",
|
1360 |
+
"lstrip": false,
|
1361 |
+
"normalized": false,
|
1362 |
+
"rstrip": false,
|
1363 |
+
"single_word": false,
|
1364 |
+
"special": false
|
1365 |
+
},
|
1366 |
+
"170": {
|
1367 |
+
"content": "<extra_id_165>",
|
1368 |
+
"lstrip": false,
|
1369 |
+
"normalized": false,
|
1370 |
+
"rstrip": false,
|
1371 |
+
"single_word": false,
|
1372 |
+
"special": false
|
1373 |
+
},
|
1374 |
+
"171": {
|
1375 |
+
"content": "<extra_id_166>",
|
1376 |
+
"lstrip": false,
|
1377 |
+
"normalized": false,
|
1378 |
+
"rstrip": false,
|
1379 |
+
"single_word": false,
|
1380 |
+
"special": false
|
1381 |
+
},
|
1382 |
+
"172": {
|
1383 |
+
"content": "<extra_id_167>",
|
1384 |
+
"lstrip": false,
|
1385 |
+
"normalized": false,
|
1386 |
+
"rstrip": false,
|
1387 |
+
"single_word": false,
|
1388 |
+
"special": false
|
1389 |
+
},
|
1390 |
+
"173": {
|
1391 |
+
"content": "<extra_id_168>",
|
1392 |
+
"lstrip": false,
|
1393 |
+
"normalized": false,
|
1394 |
+
"rstrip": false,
|
1395 |
+
"single_word": false,
|
1396 |
+
"special": false
|
1397 |
+
},
|
1398 |
+
"174": {
|
1399 |
+
"content": "<extra_id_169>",
|
1400 |
+
"lstrip": false,
|
1401 |
+
"normalized": false,
|
1402 |
+
"rstrip": false,
|
1403 |
+
"single_word": false,
|
1404 |
+
"special": false
|
1405 |
+
},
|
1406 |
+
"175": {
|
1407 |
+
"content": "<extra_id_170>",
|
1408 |
+
"lstrip": false,
|
1409 |
+
"normalized": false,
|
1410 |
+
"rstrip": false,
|
1411 |
+
"single_word": false,
|
1412 |
+
"special": false
|
1413 |
+
},
|
1414 |
+
"176": {
|
1415 |
+
"content": "<extra_id_171>",
|
1416 |
+
"lstrip": false,
|
1417 |
+
"normalized": false,
|
1418 |
+
"rstrip": false,
|
1419 |
+
"single_word": false,
|
1420 |
+
"special": false
|
1421 |
+
},
|
1422 |
+
"177": {
|
1423 |
+
"content": "<extra_id_172>",
|
1424 |
+
"lstrip": false,
|
1425 |
+
"normalized": false,
|
1426 |
+
"rstrip": false,
|
1427 |
+
"single_word": false,
|
1428 |
+
"special": false
|
1429 |
+
},
|
1430 |
+
"178": {
|
1431 |
+
"content": "<extra_id_173>",
|
1432 |
+
"lstrip": false,
|
1433 |
+
"normalized": false,
|
1434 |
+
"rstrip": false,
|
1435 |
+
"single_word": false,
|
1436 |
+
"special": false
|
1437 |
+
},
|
1438 |
+
"179": {
|
1439 |
+
"content": "<extra_id_174>",
|
1440 |
+
"lstrip": false,
|
1441 |
+
"normalized": false,
|
1442 |
+
"rstrip": false,
|
1443 |
+
"single_word": false,
|
1444 |
+
"special": false
|
1445 |
+
},
|
1446 |
+
"180": {
|
1447 |
+
"content": "<extra_id_175>",
|
1448 |
+
"lstrip": false,
|
1449 |
+
"normalized": false,
|
1450 |
+
"rstrip": false,
|
1451 |
+
"single_word": false,
|
1452 |
+
"special": false
|
1453 |
+
},
|
1454 |
+
"181": {
|
1455 |
+
"content": "<extra_id_176>",
|
1456 |
+
"lstrip": false,
|
1457 |
+
"normalized": false,
|
1458 |
+
"rstrip": false,
|
1459 |
+
"single_word": false,
|
1460 |
+
"special": false
|
1461 |
+
},
|
1462 |
+
"182": {
|
1463 |
+
"content": "<extra_id_177>",
|
1464 |
+
"lstrip": false,
|
1465 |
+
"normalized": false,
|
1466 |
+
"rstrip": false,
|
1467 |
+
"single_word": false,
|
1468 |
+
"special": false
|
1469 |
+
},
|
1470 |
+
"183": {
|
1471 |
+
"content": "<extra_id_178>",
|
1472 |
+
"lstrip": false,
|
1473 |
+
"normalized": false,
|
1474 |
+
"rstrip": false,
|
1475 |
+
"single_word": false,
|
1476 |
+
"special": false
|
1477 |
+
},
|
1478 |
+
"184": {
|
1479 |
+
"content": "<extra_id_179>",
|
1480 |
+
"lstrip": false,
|
1481 |
+
"normalized": false,
|
1482 |
+
"rstrip": false,
|
1483 |
+
"single_word": false,
|
1484 |
+
"special": false
|
1485 |
+
},
|
1486 |
+
"185": {
|
1487 |
+
"content": "<extra_id_180>",
|
1488 |
+
"lstrip": false,
|
1489 |
+
"normalized": false,
|
1490 |
+
"rstrip": false,
|
1491 |
+
"single_word": false,
|
1492 |
+
"special": false
|
1493 |
+
},
|
1494 |
+
"186": {
|
1495 |
+
"content": "<extra_id_181>",
|
1496 |
+
"lstrip": false,
|
1497 |
+
"normalized": false,
|
1498 |
+
"rstrip": false,
|
1499 |
+
"single_word": false,
|
1500 |
+
"special": false
|
1501 |
+
},
|
1502 |
+
"187": {
|
1503 |
+
"content": "<extra_id_182>",
|
1504 |
+
"lstrip": false,
|
1505 |
+
"normalized": false,
|
1506 |
+
"rstrip": false,
|
1507 |
+
"single_word": false,
|
1508 |
+
"special": false
|
1509 |
+
},
|
1510 |
+
"188": {
|
1511 |
+
"content": "<extra_id_183>",
|
1512 |
+
"lstrip": false,
|
1513 |
+
"normalized": false,
|
1514 |
+
"rstrip": false,
|
1515 |
+
"single_word": false,
|
1516 |
+
"special": false
|
1517 |
+
},
|
1518 |
+
"189": {
|
1519 |
+
"content": "<extra_id_184>",
|
1520 |
+
"lstrip": false,
|
1521 |
+
"normalized": false,
|
1522 |
+
"rstrip": false,
|
1523 |
+
"single_word": false,
|
1524 |
+
"special": false
|
1525 |
+
},
|
1526 |
+
"190": {
|
1527 |
+
"content": "<extra_id_185>",
|
1528 |
+
"lstrip": false,
|
1529 |
+
"normalized": false,
|
1530 |
+
"rstrip": false,
|
1531 |
+
"single_word": false,
|
1532 |
+
"special": false
|
1533 |
+
},
|
1534 |
+
"191": {
|
1535 |
+
"content": "<extra_id_186>",
|
1536 |
+
"lstrip": false,
|
1537 |
+
"normalized": false,
|
1538 |
+
"rstrip": false,
|
1539 |
+
"single_word": false,
|
1540 |
+
"special": false
|
1541 |
+
},
|
1542 |
+
"192": {
|
1543 |
+
"content": "<extra_id_187>",
|
1544 |
+
"lstrip": false,
|
1545 |
+
"normalized": false,
|
1546 |
+
"rstrip": false,
|
1547 |
+
"single_word": false,
|
1548 |
+
"special": false
|
1549 |
+
},
|
1550 |
+
"193": {
|
1551 |
+
"content": "<extra_id_188>",
|
1552 |
+
"lstrip": false,
|
1553 |
+
"normalized": false,
|
1554 |
+
"rstrip": false,
|
1555 |
+
"single_word": false,
|
1556 |
+
"special": false
|
1557 |
+
},
|
1558 |
+
"194": {
|
1559 |
+
"content": "<extra_id_189>",
|
1560 |
+
"lstrip": false,
|
1561 |
+
"normalized": false,
|
1562 |
+
"rstrip": false,
|
1563 |
+
"single_word": false,
|
1564 |
+
"special": false
|
1565 |
+
},
|
1566 |
+
"195": {
|
1567 |
+
"content": "<extra_id_190>",
|
1568 |
+
"lstrip": false,
|
1569 |
+
"normalized": false,
|
1570 |
+
"rstrip": false,
|
1571 |
+
"single_word": false,
|
1572 |
+
"special": false
|
1573 |
+
},
|
1574 |
+
"196": {
|
1575 |
+
"content": "<extra_id_191>",
|
1576 |
+
"lstrip": false,
|
1577 |
+
"normalized": false,
|
1578 |
+
"rstrip": false,
|
1579 |
+
"single_word": false,
|
1580 |
+
"special": false
|
1581 |
+
},
|
1582 |
+
"197": {
|
1583 |
+
"content": "<extra_id_192>",
|
1584 |
+
"lstrip": false,
|
1585 |
+
"normalized": false,
|
1586 |
+
"rstrip": false,
|
1587 |
+
"single_word": false,
|
1588 |
+
"special": false
|
1589 |
+
},
|
1590 |
+
"198": {
|
1591 |
+
"content": "<extra_id_193>",
|
1592 |
+
"lstrip": false,
|
1593 |
+
"normalized": false,
|
1594 |
+
"rstrip": false,
|
1595 |
+
"single_word": false,
|
1596 |
+
"special": false
|
1597 |
+
},
|
1598 |
+
"199": {
|
1599 |
+
"content": "<extra_id_194>",
|
1600 |
+
"lstrip": false,
|
1601 |
+
"normalized": false,
|
1602 |
+
"rstrip": false,
|
1603 |
+
"single_word": false,
|
1604 |
+
"special": false
|
1605 |
+
},
|
1606 |
+
"200": {
|
1607 |
+
"content": "<extra_id_195>",
|
1608 |
+
"lstrip": false,
|
1609 |
+
"normalized": false,
|
1610 |
+
"rstrip": false,
|
1611 |
+
"single_word": false,
|
1612 |
+
"special": false
|
1613 |
+
},
|
1614 |
+
"201": {
|
1615 |
+
"content": "<extra_id_196>",
|
1616 |
+
"lstrip": false,
|
1617 |
+
"normalized": false,
|
1618 |
+
"rstrip": false,
|
1619 |
+
"single_word": false,
|
1620 |
+
"special": false
|
1621 |
+
},
|
1622 |
+
"202": {
|
1623 |
+
"content": "<extra_id_197>",
|
1624 |
+
"lstrip": false,
|
1625 |
+
"normalized": false,
|
1626 |
+
"rstrip": false,
|
1627 |
+
"single_word": false,
|
1628 |
+
"special": false
|
1629 |
+
},
|
1630 |
+
"203": {
|
1631 |
+
"content": "<extra_id_198>",
|
1632 |
+
"lstrip": false,
|
1633 |
+
"normalized": false,
|
1634 |
+
"rstrip": false,
|
1635 |
+
"single_word": false,
|
1636 |
+
"special": false
|
1637 |
+
},
|
1638 |
+
"204": {
|
1639 |
+
"content": "<extra_id_199>",
|
1640 |
+
"lstrip": false,
|
1641 |
+
"normalized": false,
|
1642 |
+
"rstrip": false,
|
1643 |
+
"single_word": false,
|
1644 |
+
"special": false
|
1645 |
+
},
|
1646 |
+
"205": {
|
1647 |
+
"content": "<extra_id_200>",
|
1648 |
+
"lstrip": false,
|
1649 |
+
"normalized": false,
|
1650 |
+
"rstrip": false,
|
1651 |
+
"single_word": false,
|
1652 |
+
"special": false
|
1653 |
+
},
|
1654 |
+
"206": {
|
1655 |
+
"content": "<extra_id_201>",
|
1656 |
+
"lstrip": false,
|
1657 |
+
"normalized": false,
|
1658 |
+
"rstrip": false,
|
1659 |
+
"single_word": false,
|
1660 |
+
"special": false
|
1661 |
+
},
|
1662 |
+
"207": {
|
1663 |
+
"content": "<extra_id_202>",
|
1664 |
+
"lstrip": false,
|
1665 |
+
"normalized": false,
|
1666 |
+
"rstrip": false,
|
1667 |
+
"single_word": false,
|
1668 |
+
"special": false
|
1669 |
+
},
|
1670 |
+
"208": {
|
1671 |
+
"content": "<extra_id_203>",
|
1672 |
+
"lstrip": false,
|
1673 |
+
"normalized": false,
|
1674 |
+
"rstrip": false,
|
1675 |
+
"single_word": false,
|
1676 |
+
"special": false
|
1677 |
+
},
|
1678 |
+
"209": {
|
1679 |
+
"content": "<extra_id_204>",
|
1680 |
+
"lstrip": false,
|
1681 |
+
"normalized": false,
|
1682 |
+
"rstrip": false,
|
1683 |
+
"single_word": false,
|
1684 |
+
"special": false
|
1685 |
+
},
|
1686 |
+
"210": {
|
1687 |
+
"content": "<extra_id_205>",
|
1688 |
+
"lstrip": false,
|
1689 |
+
"normalized": false,
|
1690 |
+
"rstrip": false,
|
1691 |
+
"single_word": false,
|
1692 |
+
"special": false
|
1693 |
+
},
|
1694 |
+
"211": {
|
1695 |
+
"content": "<extra_id_206>",
|
1696 |
+
"lstrip": false,
|
1697 |
+
"normalized": false,
|
1698 |
+
"rstrip": false,
|
1699 |
+
"single_word": false,
|
1700 |
+
"special": false
|
1701 |
+
},
|
1702 |
+
"212": {
|
1703 |
+
"content": "<extra_id_207>",
|
1704 |
+
"lstrip": false,
|
1705 |
+
"normalized": false,
|
1706 |
+
"rstrip": false,
|
1707 |
+
"single_word": false,
|
1708 |
+
"special": false
|
1709 |
+
},
|
1710 |
+
"213": {
|
1711 |
+
"content": "<extra_id_208>",
|
1712 |
+
"lstrip": false,
|
1713 |
+
"normalized": false,
|
1714 |
+
"rstrip": false,
|
1715 |
+
"single_word": false,
|
1716 |
+
"special": false
|
1717 |
+
},
|
1718 |
+
"214": {
|
1719 |
+
"content": "<extra_id_209>",
|
1720 |
+
"lstrip": false,
|
1721 |
+
"normalized": false,
|
1722 |
+
"rstrip": false,
|
1723 |
+
"single_word": false,
|
1724 |
+
"special": false
|
1725 |
+
},
|
1726 |
+
"215": {
|
1727 |
+
"content": "<extra_id_210>",
|
1728 |
+
"lstrip": false,
|
1729 |
+
"normalized": false,
|
1730 |
+
"rstrip": false,
|
1731 |
+
"single_word": false,
|
1732 |
+
"special": false
|
1733 |
+
},
|
1734 |
+
"216": {
|
1735 |
+
"content": "<extra_id_211>",
|
1736 |
+
"lstrip": false,
|
1737 |
+
"normalized": false,
|
1738 |
+
"rstrip": false,
|
1739 |
+
"single_word": false,
|
1740 |
+
"special": false
|
1741 |
+
},
|
1742 |
+
"217": {
|
1743 |
+
"content": "<extra_id_212>",
|
1744 |
+
"lstrip": false,
|
1745 |
+
"normalized": false,
|
1746 |
+
"rstrip": false,
|
1747 |
+
"single_word": false,
|
1748 |
+
"special": false
|
1749 |
+
},
|
1750 |
+
"218": {
|
1751 |
+
"content": "<extra_id_213>",
|
1752 |
+
"lstrip": false,
|
1753 |
+
"normalized": false,
|
1754 |
+
"rstrip": false,
|
1755 |
+
"single_word": false,
|
1756 |
+
"special": false
|
1757 |
+
},
|
1758 |
+
"219": {
|
1759 |
+
"content": "<extra_id_214>",
|
1760 |
+
"lstrip": false,
|
1761 |
+
"normalized": false,
|
1762 |
+
"rstrip": false,
|
1763 |
+
"single_word": false,
|
1764 |
+
"special": false
|
1765 |
+
},
|
1766 |
+
"220": {
|
1767 |
+
"content": "<extra_id_215>",
|
1768 |
+
"lstrip": false,
|
1769 |
+
"normalized": false,
|
1770 |
+
"rstrip": false,
|
1771 |
+
"single_word": false,
|
1772 |
+
"special": false
|
1773 |
+
},
|
1774 |
+
"221": {
|
1775 |
+
"content": "<extra_id_216>",
|
1776 |
+
"lstrip": false,
|
1777 |
+
"normalized": false,
|
1778 |
+
"rstrip": false,
|
1779 |
+
"single_word": false,
|
1780 |
+
"special": false
|
1781 |
+
},
|
1782 |
+
"222": {
|
1783 |
+
"content": "<extra_id_217>",
|
1784 |
+
"lstrip": false,
|
1785 |
+
"normalized": false,
|
1786 |
+
"rstrip": false,
|
1787 |
+
"single_word": false,
|
1788 |
+
"special": false
|
1789 |
+
},
|
1790 |
+
"223": {
|
1791 |
+
"content": "<extra_id_218>",
|
1792 |
+
"lstrip": false,
|
1793 |
+
"normalized": false,
|
1794 |
+
"rstrip": false,
|
1795 |
+
"single_word": false,
|
1796 |
+
"special": false
|
1797 |
+
},
|
1798 |
+
"224": {
|
1799 |
+
"content": "<extra_id_219>",
|
1800 |
+
"lstrip": false,
|
1801 |
+
"normalized": false,
|
1802 |
+
"rstrip": false,
|
1803 |
+
"single_word": false,
|
1804 |
+
"special": false
|
1805 |
+
},
|
1806 |
+
"225": {
|
1807 |
+
"content": "<extra_id_220>",
|
1808 |
+
"lstrip": false,
|
1809 |
+
"normalized": false,
|
1810 |
+
"rstrip": false,
|
1811 |
+
"single_word": false,
|
1812 |
+
"special": false
|
1813 |
+
},
|
1814 |
+
"226": {
|
1815 |
+
"content": "<extra_id_221>",
|
1816 |
+
"lstrip": false,
|
1817 |
+
"normalized": false,
|
1818 |
+
"rstrip": false,
|
1819 |
+
"single_word": false,
|
1820 |
+
"special": false
|
1821 |
+
},
|
1822 |
+
"227": {
|
1823 |
+
"content": "<extra_id_222>",
|
1824 |
+
"lstrip": false,
|
1825 |
+
"normalized": false,
|
1826 |
+
"rstrip": false,
|
1827 |
+
"single_word": false,
|
1828 |
+
"special": false
|
1829 |
+
},
|
1830 |
+
"228": {
|
1831 |
+
"content": "<extra_id_223>",
|
1832 |
+
"lstrip": false,
|
1833 |
+
"normalized": false,
|
1834 |
+
"rstrip": false,
|
1835 |
+
"single_word": false,
|
1836 |
+
"special": false
|
1837 |
+
},
|
1838 |
+
"229": {
|
1839 |
+
"content": "<extra_id_224>",
|
1840 |
+
"lstrip": false,
|
1841 |
+
"normalized": false,
|
1842 |
+
"rstrip": false,
|
1843 |
+
"single_word": false,
|
1844 |
+
"special": false
|
1845 |
+
},
|
1846 |
+
"230": {
|
1847 |
+
"content": "<extra_id_225>",
|
1848 |
+
"lstrip": false,
|
1849 |
+
"normalized": false,
|
1850 |
+
"rstrip": false,
|
1851 |
+
"single_word": false,
|
1852 |
+
"special": false
|
1853 |
+
},
|
1854 |
+
"231": {
|
1855 |
+
"content": "<extra_id_226>",
|
1856 |
+
"lstrip": false,
|
1857 |
+
"normalized": false,
|
1858 |
+
"rstrip": false,
|
1859 |
+
"single_word": false,
|
1860 |
+
"special": false
|
1861 |
+
},
|
1862 |
+
"232": {
|
1863 |
+
"content": "<extra_id_227>",
|
1864 |
+
"lstrip": false,
|
1865 |
+
"normalized": false,
|
1866 |
+
"rstrip": false,
|
1867 |
+
"single_word": false,
|
1868 |
+
"special": false
|
1869 |
+
},
|
1870 |
+
"233": {
|
1871 |
+
"content": "<extra_id_228>",
|
1872 |
+
"lstrip": false,
|
1873 |
+
"normalized": false,
|
1874 |
+
"rstrip": false,
|
1875 |
+
"single_word": false,
|
1876 |
+
"special": false
|
1877 |
+
},
|
1878 |
+
"234": {
|
1879 |
+
"content": "<extra_id_229>",
|
1880 |
+
"lstrip": false,
|
1881 |
+
"normalized": false,
|
1882 |
+
"rstrip": false,
|
1883 |
+
"single_word": false,
|
1884 |
+
"special": false
|
1885 |
+
},
|
1886 |
+
"235": {
|
1887 |
+
"content": "<extra_id_230>",
|
1888 |
+
"lstrip": false,
|
1889 |
+
"normalized": false,
|
1890 |
+
"rstrip": false,
|
1891 |
+
"single_word": false,
|
1892 |
+
"special": false
|
1893 |
+
},
|
1894 |
+
"236": {
|
1895 |
+
"content": "<extra_id_231>",
|
1896 |
+
"lstrip": false,
|
1897 |
+
"normalized": false,
|
1898 |
+
"rstrip": false,
|
1899 |
+
"single_word": false,
|
1900 |
+
"special": false
|
1901 |
+
},
|
1902 |
+
"237": {
|
1903 |
+
"content": "<extra_id_232>",
|
1904 |
+
"lstrip": false,
|
1905 |
+
"normalized": false,
|
1906 |
+
"rstrip": false,
|
1907 |
+
"single_word": false,
|
1908 |
+
"special": false
|
1909 |
+
},
|
1910 |
+
"238": {
|
1911 |
+
"content": "<extra_id_233>",
|
1912 |
+
"lstrip": false,
|
1913 |
+
"normalized": false,
|
1914 |
+
"rstrip": false,
|
1915 |
+
"single_word": false,
|
1916 |
+
"special": false
|
1917 |
+
},
|
1918 |
+
"239": {
|
1919 |
+
"content": "<extra_id_234>",
|
1920 |
+
"lstrip": false,
|
1921 |
+
"normalized": false,
|
1922 |
+
"rstrip": false,
|
1923 |
+
"single_word": false,
|
1924 |
+
"special": false
|
1925 |
+
},
|
1926 |
+
"240": {
|
1927 |
+
"content": "<extra_id_235>",
|
1928 |
+
"lstrip": false,
|
1929 |
+
"normalized": false,
|
1930 |
+
"rstrip": false,
|
1931 |
+
"single_word": false,
|
1932 |
+
"special": false
|
1933 |
+
},
|
1934 |
+
"241": {
|
1935 |
+
"content": "<extra_id_236>",
|
1936 |
+
"lstrip": false,
|
1937 |
+
"normalized": false,
|
1938 |
+
"rstrip": false,
|
1939 |
+
"single_word": false,
|
1940 |
+
"special": false
|
1941 |
+
},
|
1942 |
+
"242": {
|
1943 |
+
"content": "<extra_id_237>",
|
1944 |
+
"lstrip": false,
|
1945 |
+
"normalized": false,
|
1946 |
+
"rstrip": false,
|
1947 |
+
"single_word": false,
|
1948 |
+
"special": false
|
1949 |
+
},
|
1950 |
+
"243": {
|
1951 |
+
"content": "<extra_id_238>",
|
1952 |
+
"lstrip": false,
|
1953 |
+
"normalized": false,
|
1954 |
+
"rstrip": false,
|
1955 |
+
"single_word": false,
|
1956 |
+
"special": false
|
1957 |
+
},
|
1958 |
+
"244": {
|
1959 |
+
"content": "<extra_id_239>",
|
1960 |
+
"lstrip": false,
|
1961 |
+
"normalized": false,
|
1962 |
+
"rstrip": false,
|
1963 |
+
"single_word": false,
|
1964 |
+
"special": false
|
1965 |
+
},
|
1966 |
+
"245": {
|
1967 |
+
"content": "<extra_id_240>",
|
1968 |
+
"lstrip": false,
|
1969 |
+
"normalized": false,
|
1970 |
+
"rstrip": false,
|
1971 |
+
"single_word": false,
|
1972 |
+
"special": false
|
1973 |
+
},
|
1974 |
+
"246": {
|
1975 |
+
"content": "<extra_id_241>",
|
1976 |
+
"lstrip": false,
|
1977 |
+
"normalized": false,
|
1978 |
+
"rstrip": false,
|
1979 |
+
"single_word": false,
|
1980 |
+
"special": false
|
1981 |
+
},
|
1982 |
+
"247": {
|
1983 |
+
"content": "<extra_id_242>",
|
1984 |
+
"lstrip": false,
|
1985 |
+
"normalized": false,
|
1986 |
+
"rstrip": false,
|
1987 |
+
"single_word": false,
|
1988 |
+
"special": false
|
1989 |
+
},
|
1990 |
+
"248": {
|
1991 |
+
"content": "<extra_id_243>",
|
1992 |
+
"lstrip": false,
|
1993 |
+
"normalized": false,
|
1994 |
+
"rstrip": false,
|
1995 |
+
"single_word": false,
|
1996 |
+
"special": false
|
1997 |
+
},
|
1998 |
+
"249": {
|
1999 |
+
"content": "<extra_id_244>",
|
2000 |
+
"lstrip": false,
|
2001 |
+
"normalized": false,
|
2002 |
+
"rstrip": false,
|
2003 |
+
"single_word": false,
|
2004 |
+
"special": false
|
2005 |
+
},
|
2006 |
+
"250": {
|
2007 |
+
"content": "<extra_id_245>",
|
2008 |
+
"lstrip": false,
|
2009 |
+
"normalized": false,
|
2010 |
+
"rstrip": false,
|
2011 |
+
"single_word": false,
|
2012 |
+
"special": false
|
2013 |
+
},
|
2014 |
+
"251": {
|
2015 |
+
"content": "<extra_id_246>",
|
2016 |
+
"lstrip": false,
|
2017 |
+
"normalized": false,
|
2018 |
+
"rstrip": false,
|
2019 |
+
"single_word": false,
|
2020 |
+
"special": false
|
2021 |
+
},
|
2022 |
+
"252": {
|
2023 |
+
"content": "<extra_id_247>",
|
2024 |
+
"lstrip": false,
|
2025 |
+
"normalized": false,
|
2026 |
+
"rstrip": false,
|
2027 |
+
"single_word": false,
|
2028 |
+
"special": false
|
2029 |
+
},
|
2030 |
+
"253": {
|
2031 |
+
"content": "<extra_id_248>",
|
2032 |
+
"lstrip": false,
|
2033 |
+
"normalized": false,
|
2034 |
+
"rstrip": false,
|
2035 |
+
"single_word": false,
|
2036 |
+
"special": false
|
2037 |
+
},
|
2038 |
+
"254": {
|
2039 |
+
"content": "<extra_id_249>",
|
2040 |
+
"lstrip": false,
|
2041 |
+
"normalized": false,
|
2042 |
+
"rstrip": false,
|
2043 |
+
"single_word": false,
|
2044 |
+
"special": false
|
2045 |
+
},
|
2046 |
+
"255": {
|
2047 |
+
"content": "<extra_id_250>",
|
2048 |
+
"lstrip": false,
|
2049 |
+
"normalized": false,
|
2050 |
+
"rstrip": false,
|
2051 |
+
"single_word": false,
|
2052 |
+
"special": false
|
2053 |
+
},
|
2054 |
+
"256": {
|
2055 |
+
"content": "<extra_id_251>",
|
2056 |
+
"lstrip": false,
|
2057 |
+
"normalized": false,
|
2058 |
+
"rstrip": false,
|
2059 |
+
"single_word": false,
|
2060 |
+
"special": false
|
2061 |
+
},
|
2062 |
+
"257": {
|
2063 |
+
"content": "<extra_id_252>",
|
2064 |
+
"lstrip": false,
|
2065 |
+
"normalized": false,
|
2066 |
+
"rstrip": false,
|
2067 |
+
"single_word": false,
|
2068 |
+
"special": false
|
2069 |
+
},
|
2070 |
+
"258": {
|
2071 |
+
"content": "<extra_id_253>",
|
2072 |
+
"lstrip": false,
|
2073 |
+
"normalized": false,
|
2074 |
+
"rstrip": false,
|
2075 |
+
"single_word": false,
|
2076 |
+
"special": false
|
2077 |
+
},
|
2078 |
+
"259": {
|
2079 |
+
"content": "<extra_id_254>",
|
2080 |
+
"lstrip": false,
|
2081 |
+
"normalized": false,
|
2082 |
+
"rstrip": false,
|
2083 |
+
"single_word": false,
|
2084 |
+
"special": false
|
2085 |
+
},
|
2086 |
+
"260": {
|
2087 |
+
"content": "<extra_id_255>",
|
2088 |
+
"lstrip": false,
|
2089 |
+
"normalized": false,
|
2090 |
+
"rstrip": false,
|
2091 |
+
"single_word": false,
|
2092 |
+
"special": false
|
2093 |
+
}
|
2094 |
+
},
|
2095 |
+
"bos_token": "<s>",
|
2096 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'assistant' %}{% else %}{% set role = message['role'] %}{% endif %}<|im_start|>{{ role }}\n{{ message['content'] | trim }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n'}}{% endif %}",
|
2097 |
+
"clean_up_tokenization_spaces": false,
|
2098 |
+
"eos_token": "<|im_end|>",
|
2099 |
+
"extra_special_tokens": {},
|
2100 |
+
"legacy": true,
|
2101 |
+
"model_max_length": 1000000000000000019884624838656,
|
2102 |
+
"pad_token": "</s>",
|
2103 |
+
"sp_model_kwargs": {},
|
2104 |
+
"spaces_between_special_tokens": false,
|
2105 |
+
"tokenizer_class": "LlamaTokenizer",
|
2106 |
+
"unk_token": "<unk>",
|
2107 |
+
"use_default_system_prompt": false,
|
2108 |
+
"use_fast": true
|
2109 |
+
}
|