Sharathhebbar24
commited on
Commit
•
f3d47c3
1
Parent(s):
9bb450c
Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer.json +2 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -1,24 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"pad_token": "<|endoftext|>",
|
17 |
-
"unk_token":
|
18 |
-
"content": "<|endoftext|>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized":
|
13 |
"special": true
|
14 |
}
|
15 |
],
|
@@ -40,6 +40,7 @@
|
|
40 |
"end_of_word_suffix": "",
|
41 |
"fuse_unk": false,
|
42 |
"byte_fallback": false,
|
|
|
43 |
"vocab": {
|
44 |
"!": 0,
|
45 |
"\"": 1,
|
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": true,
|
13 |
"special": true
|
14 |
}
|
15 |
],
|
|
|
40 |
"end_of_word_suffix": "",
|
41 |
"fuse_unk": false,
|
42 |
"byte_fallback": false,
|
43 |
+
"ignore_merges": false,
|
44 |
"vocab": {
|
45 |
"!": 0,
|
46 |
"\"": 1,
|
tokenizer_config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"50256": {
|
5 |
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
-
"normalized":
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
|
|
4 |
"50256": {
|
5 |
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|