karthikqnq
commited on
Commit
•
ab0b188
1
Parent(s):
3a9d5b0
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +1 -7
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -20,13 +20,7 @@
|
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
-
"pad_token":
|
24 |
-
"content": "<pad>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
"sep_token": {
|
31 |
"content": "<sep>",
|
32 |
"lstrip": false,
|
|
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
+
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"sep_token": {
|
25 |
"content": "<sep>",
|
26 |
"lstrip": false,
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -41,7 +41,7 @@
|
|
41 |
"errors": "replace",
|
42 |
"mask_token": "<mask>",
|
43 |
"model_max_length": 1024,
|
44 |
-
"pad_token": "
|
45 |
"sep_token": "<sep>",
|
46 |
"tokenizer_class": "GPT2Tokenizer",
|
47 |
"unk_token": "<|endoftext|>"
|
|
|
41 |
"errors": "replace",
|
42 |
"mask_token": "<mask>",
|
43 |
"model_max_length": 1024,
|
44 |
+
"pad_token": "<|endoftext|>",
|
45 |
"sep_token": "<sep>",
|
46 |
"tokenizer_class": "GPT2Tokenizer",
|
47 |
"unk_token": "<|endoftext|>"
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|