Commit
•
f7ad4e7
1
Parent(s):
8a266d3
Upload processor
Browse files- special_tokens_map.json +9 -0
- tokenizer_config.json +5 -1
special_tokens_map.json
CHANGED
@@ -1,4 +1,13 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
|
|
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>",
|
13 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space":
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -44,6 +44,9 @@
|
|
44 |
"special": true
|
45 |
}
|
46 |
},
|
|
|
|
|
|
|
47 |
"bos_token": "<s>",
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
"eos_token": "</s>",
|
@@ -53,6 +56,7 @@
|
|
53 |
"padding_side": "right",
|
54 |
"processor_class": "MPLUGDocOwlProcessor",
|
55 |
"sp_model_kwargs": {},
|
|
|
56 |
"tokenizer_class": "LlamaTokenizer",
|
57 |
"unk_token": "<unk>",
|
58 |
"use_default_system_prompt": false
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
44 |
"special": true
|
45 |
}
|
46 |
},
|
47 |
+
"additional_special_tokens": [
|
48 |
+
"<image>"
|
49 |
+
],
|
50 |
"bos_token": "<s>",
|
51 |
"clean_up_tokenization_spaces": false,
|
52 |
"eos_token": "</s>",
|
|
|
56 |
"padding_side": "right",
|
57 |
"processor_class": "MPLUGDocOwlProcessor",
|
58 |
"sp_model_kwargs": {},
|
59 |
+
"spaces_between_special_tokens": false,
|
60 |
"tokenizer_class": "LlamaTokenizer",
|
61 |
"unk_token": "<unk>",
|
62 |
"use_default_system_prompt": false
|