Set left padding side and <unk> token as pad token
Browse files- special_tokens_map.json +2 -14
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
@@ -1,12 +1,6 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
|
4 |
-
"content": "<image>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
}
|
10 |
],
|
11 |
"bos_token": {
|
12 |
"content": "<s>",
|
@@ -22,13 +16,7 @@
|
|
22 |
"rstrip": false,
|
23 |
"single_word": false
|
24 |
},
|
25 |
-
"pad_token":
|
26 |
-
"content": "<pad>",
|
27 |
-
"lstrip": false,
|
28 |
-
"normalized": false,
|
29 |
-
"rstrip": false,
|
30 |
-
"single_word": false
|
31 |
-
},
|
32 |
"unk_token": {
|
33 |
"content": "<unk>",
|
34 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"<image>"
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
],
|
5 |
"bos_token": {
|
6 |
"content": "<s>",
|
|
|
16 |
"rstrip": false,
|
17 |
"single_word": false
|
18 |
},
|
19 |
+
"pad_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"unk_token": {
|
21 |
"content": "<unk>",
|
22 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -52,8 +52,8 @@
|
|
52 |
"eos_token": "</s>",
|
53 |
"legacy": false,
|
54 |
"model_max_length": 4096,
|
55 |
-
"pad_token": "<
|
56 |
-
"padding_side": "
|
57 |
"processor_class": "LlavaProcessor",
|
58 |
"sp_model_kwargs": {},
|
59 |
"spaces_between_special_tokens": false,
|
|
|
52 |
"eos_token": "</s>",
|
53 |
"legacy": false,
|
54 |
"model_max_length": 4096,
|
55 |
+
"pad_token": "<unk>",
|
56 |
+
"padding_side": "left",
|
57 |
"processor_class": "LlavaProcessor",
|
58 |
"sp_model_kwargs": {},
|
59 |
"spaces_between_special_tokens": false,
|