Upload processor

added_tokens.json

@@ -1,12 +1,12 @@
 {
-  "</s_answer>": 57530,
-  "</s_question>": 57528,
-  "<no/>": 57526,
-  "<s_answer>": 57529,
-  "<s_docvqa>": 57531,
-  "<s_iitcdip>": 57523,
-  "<s_question>": 57527,
-  "<s_synthdog>": 57524,
+  "</s_answer>": 57523,
+  "</s_question>": 57524,
+  "<no/>": 57525,
+  "<s_answer>": 57526,
+  "<s_docvqa>": 57527,
+  "<s_iitcdip>": 57528,
+  "<s_question>": 57529,
+  "<s_synthdog>": 57530,
   "<sep/>": 57522,
-  "<yes/>": 57525
+  "<yes/>": 57531
 }

special_tokens_map.json

@@ -1,7 +1,14 @@
 {
   "additional_special_tokens": [
+    "</s_answer>",
+    "</s_question>",
+    "<no/>",
+    "<s_answer>",
+    "<s_docvqa>",
     "<s_iitcdip>",
-    "<s_synthdog>"
+    "<s_question>",
+    "<s_synthdog>",
+    "<yes/>"
   ],
   "bos_token": {
     "content": "<s>",

tokenizer.json

@@ -73,25 +73,25 @@
     },
     {
       "id": 57523,
-      "content": "<s_iitcdip>",
+      "content": "</s_answer>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     },
     {
       "id": 57524,
-      "content": "<s_synthdog>",
+      "content": "</s_question>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     },
     {
       "id": 57525,
-      "content": "<yes/>",
+      "content": "<no/>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -100,7 +100,7 @@
     },
     {
       "id": 57526,
-      "content": "<no/>",
+      "content": "<s_answer>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -109,7 +109,7 @@
     },
     {
       "id": 57527,
-      "content": "<s_question>",
+      "content": "<s_docvqa>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -118,16 +118,16 @@
     },
     {
       "id": 57528,
-      "content": "</s_question>",
+      "content": "<s_iitcdip>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
-      "special": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 57529,
-      "content": "<s_answer>",
+      "content": "<s_question>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -136,16 +136,16 @@
     },
     {
       "id": 57530,
-      "content": "</s_answer>",
+      "content": "<s_synthdog>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
-      "special": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 57531,
-      "content": "<s_docvqa>",
+      "content": "<yes/>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -49,23 +49,23 @@
       "special": false
     },
     "57523": {
-      "content": "<s_iitcdip>",
+      "content": "</s_answer>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "57524": {
-      "content": "<s_synthdog>",
+      "content": "</s_question>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "57525": {
-      "content": "<yes/>",
+      "content": "<no/>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -73,7 +73,7 @@
       "special": false
     },
     "57526": {
-      "content": "<no/>",
+      "content": "<s_answer>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -81,7 +81,7 @@
       "special": false
     },
     "57527": {
-      "content": "<s_question>",
+      "content": "<s_docvqa>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -89,15 +89,15 @@
       "special": false
     },
     "57528": {
-      "content": "</s_question>",
+      "content": "<s_iitcdip>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "57529": {
-      "content": "<s_answer>",
+      "content": "<s_question>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -105,15 +105,15 @@
       "special": false
     },
     "57530": {
-      "content": "</s_answer>",
+      "content": "<s_synthdog>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "57531": {
-      "content": "<s_docvqa>",
+      "content": "<yes/>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -122,8 +122,15 @@
     }
   },
   "additional_special_tokens": [
+    "</s_answer>",
+    "</s_question>",
+    "<no/>",
+    "<s_answer>",
+    "<s_docvqa>",
     "<s_iitcdip>",
-    "<s_synthdog>"
+    "<s_question>",
+    "<s_synthdog>",
+    "<yes/>"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,