fajarluhung
/

donut-ktp

Image-Text-to-Text

vision-encoder-decoder

Model card Files Files and versions

fajarluhung commited on Oct 1, 2023

Commit

9e09adf

·

1 Parent(s): 3402c32

Training in progress, epoch 0

Files changed (2) hide show

config.json +3 -3
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -85,7 +85,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57558
   },
   "decoder_start_token_id": 57557,
   "encoder": {
@@ -124,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      1280,
-      960
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
+    "vocab_size": 57559
   },
   "decoder_start_token_id": 57557,
   "encoder": {
       "1": "LABEL_1"
     },
     "image_size": [
+      960,
+      1280
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a90d23722a4b0faea9abe9ffbd43a340a6f1f43ad96b757ac3c92df187dc2d
-size 809314073

 version https://git-lfs.github.com/spec/v1
+oid sha256:204583250c471aa784c73f0f5571605fbd34756962907125181d5d44e9505f1f
+size 809318169