rathanonFA2212
/

donut-test

Image-Text-to-Text

vision-encoder-decoder

Model card Files Files and versions

rathanonFA2212 commited on Mar 13, 2024

Commit

858aad7

·

verified ·

1 Parent(s): 2f41aa9

Training done

Files changed (2) hide show

config.json +5 -5
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "naver-clova-ix/donut-base",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -85,9 +85,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57580
   },
-  "decoder_start_token_id": 57579,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -124,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      1280,
-      960
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

 {
+  "_name_or_path": "/workspace/pretrained_model/donut-base",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
+    "vocab_size": 57604
   },
+  "decoder_start_token_id": 57603,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
       "1": "LABEL_1"
     },
     "image_size": [
+      2560,
+      1920
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2ddf5e67fea36fe994daa0db6052138f4206855b6d93df3e144cccf80d903b
-size 809296024

 version https://git-lfs.github.com/spec/v1
+oid sha256:953840c89d787615c103a09a097d51dda6e487f25c2bec8b3e0c3c1cdfc18c87
+size 809394328