Upload 8 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
+  "_name_or_path": "TusharGoel/LiLT-Document-QA",
   "architectures": [
     "LiltForQuestionAnswering"
   ],

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af19cb0323181b284410f1a59cdcac62819016be9732a0f20c419a6488310f8e
+oid sha256:1e47d071230ebb0bb43143469a7ec5cf4f2c16d2dffa29200af02bba9d1ae247
 size 520801357

special_tokens_map.json

@@ -1,4 +1,11 @@
 {
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",

tokenizer.json

@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -41,7 +41,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -50,16 +50,16 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
       "id": 50264,
       "content": "<mask>",
       "single_word": false,
-      "lstrip": true,
+      "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     }
   ],

tokenizer_config.json

@@ -4,7 +4,7 @@
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,21 +28,27 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "50264": {
       "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
@@ -55,8 +61,10 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
   "only_label_first_subword": true,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
   "pad_token_box": [
     0,
@@ -65,6 +73,8 @@
     0
   ],
   "pad_token_label": -100,
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
   "sep_token_box": [
     0,
@@ -72,7 +82,10 @@
     0,
     0
   ],
+  "stride": 0,
   "tokenizer_class": "LayoutLMv3Tokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
   "unk_token": "<unk>"
 }