Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +9 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32768
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
|
|
4 |
"unk_token": "<|endoftext|>"
|
5 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
"unk_token": "<|endoftext|>"
|
6 |
}
|
tokenizer.json
CHANGED
@@ -11,6 +11,15 @@
|
|
11 |
"rstrip": false,
|
12 |
"normalized": false,
|
13 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
15 |
],
|
16 |
"normalizer": null,
|
|
|
11 |
"rstrip": false,
|
12 |
"normalized": false,
|
13 |
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 32768,
|
17 |
+
"content": "<pad>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": true,
|
22 |
+
"special": false
|
23 |
}
|
24 |
],
|
25 |
"normalizer": null,
|