hoangphu7122002ai commited on
Commit
6a810bf
1 Parent(s): f2a7a50

valid best lost

Browse files
Files changed (3) hide show
  1. added_tokens.json +4 -5
  2. tokenizer.json +3 -12
  3. tokenizer_config.json +1 -0
added_tokens.json CHANGED
@@ -1,11 +1,10 @@
1
  {
2
- "</|PROMPT|>": 50349,
3
- "<dot>": 50352,
4
- "<line>": 50350,
5
- "<vertical_bar>": 50351,
6
  "<x_end>": 50346,
7
  "<x_start>": 50345,
8
  "<y_end>": 50348,
9
  "<y_start>": 50347,
10
- "<|PROMPT|>": 50344
11
  }
 
1
  {
2
+ "<dot>": 50351,
3
+ "<line>": 50349,
4
+ "<vertical_bar>": 50350,
 
5
  "<x_end>": 50346,
6
  "<x_start>": 50345,
7
  "<y_end>": 50348,
8
  "<y_start>": 50347,
9
+ "<|BOS|>": 50344
10
  }
tokenizer.json CHANGED
@@ -946,7 +946,7 @@
946
  },
947
  {
948
  "id": 50344,
949
- "content": "<|PROMPT|>",
950
  "single_word": false,
951
  "lstrip": false,
952
  "rstrip": false,
@@ -991,15 +991,6 @@
991
  },
992
  {
993
  "id": 50349,
994
- "content": "</|PROMPT|>",
995
- "single_word": false,
996
- "lstrip": false,
997
- "rstrip": false,
998
- "normalized": true,
999
- "special": false
1000
- },
1001
- {
1002
- "id": 50350,
1003
  "content": "<line>",
1004
  "single_word": false,
1005
  "lstrip": false,
@@ -1008,7 +999,7 @@
1008
  "special": false
1009
  },
1010
  {
1011
- "id": 50351,
1012
  "content": "<vertical_bar>",
1013
  "single_word": false,
1014
  "lstrip": false,
@@ -1017,7 +1008,7 @@
1017
  "special": false
1018
  },
1019
  {
1020
- "id": 50352,
1021
  "content": "<dot>",
1022
  "single_word": false,
1023
  "lstrip": false,
 
946
  },
947
  {
948
  "id": 50344,
949
+ "content": "<|BOS|>",
950
  "single_word": false,
951
  "lstrip": false,
952
  "rstrip": false,
 
991
  },
992
  {
993
  "id": 50349,
 
 
 
 
 
 
 
 
 
994
  "content": "<line>",
995
  "single_word": false,
996
  "lstrip": false,
 
999
  "special": false
1000
  },
1001
  {
1002
+ "id": 50350,
1003
  "content": "<vertical_bar>",
1004
  "single_word": false,
1005
  "lstrip": false,
 
1008
  "special": false
1009
  },
1010
  {
1011
+ "id": 50351,
1012
  "content": "<dot>",
1013
  "single_word": false,
1014
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -104,6 +104,7 @@
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
 
107
  "model_max_length": 1000000000000000019884624838656,
108
  "pad_token": "<pad>",
109
  "processor_class": "Pix2StructProcessor",
 
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
107
+ "is_vqa": false,
108
  "model_max_length": 1000000000000000019884624838656,
109
  "pad_token": "<pad>",
110
  "processor_class": "Pix2StructProcessor",