Update tokenizer (#10)
Browse files- update (7782090a3c5cdc2e2b45e237fb4b04f48dde7636)
tokenizer_2/special_tokens_map.json
CHANGED
@@ -13,13 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "!",
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
tokenizer_2/tokenizer_config.json
CHANGED
@@ -24,7 +24,7 @@
|
|
24 |
"eos_token": "<|endoftext|>",
|
25 |
"errors": "replace",
|
26 |
"model_max_length": 77,
|
27 |
-
"pad_token": "
|
28 |
"tokenizer_class": "CLIPTokenizer",
|
29 |
"unk_token": "<|endoftext|>"
|
30 |
}
|
|
|
24 |
"eos_token": "<|endoftext|>",
|
25 |
"errors": "replace",
|
26 |
"model_max_length": 77,
|
27 |
+
"pad_token": "!",
|
28 |
"tokenizer_class": "CLIPTokenizer",
|
29 |
"unk_token": "<|endoftext|>"
|
30 |
}
|