PranavMoD
/

donut-base-sroie

Image-Text-to-Text

vision-encoder-decoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

PranavMoD commited on 11 days ago

Commit

28435c0

•

1 Parent(s): 9865bc7

Final trained model

Files changed (2) hide show

config.json +4 -4
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "naver-clova-ix/donut-base",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -49,7 +49,7 @@
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
-    "max_length": 512,
     "max_position_embeddings": 1536,
     "min_length": 0,
     "model_type": "mbart",
@@ -124,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      960,
-      720
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

 {
+  "_name_or_path": "donut-base-sroie/checkpoint-846",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
+    "max_length": 20,
     "max_position_embeddings": 1536,
     "min_length": 0,
     "model_type": "mbart",
       "1": "LABEL_1"
     },
     "image_size": [
+      720,
+      960
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c11c0aec86631a1c7ca74b65aad4137137fb89d06f5650f7bca9db0a99956bf
 size 809070744

 version https://git-lfs.github.com/spec/v1
+oid sha256:bc6468264c3faa154e7edfae8043dd7f257a4119d963dbc16e8d78f128efa6ad
 size 809070744