senga-ml
/

dnote-body

Image-Text-to-Text

vision-encoder-decoder

Model card Files Files and versions

waceke commited on Oct 19, 2025

Commit

b7c25cb

·

verified ·

1 Parent(s): caf47a2

Training in progress, epoch 0

Files changed (2) hide show

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

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "senga-ml/dnote-body_v3",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -49,7 +49,7 @@
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
-    "max_length": 768,
     "max_position_embeddings": 1536,
     "min_length": 0,
     "model_type": "mbart",
@@ -124,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      1280,
-      960
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

 {
+  "_name_or_path": "senga-ml/dnote-body",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
+    "max_length": 1536,
     "max_position_embeddings": 1536,
     "min_length": 0,
     "model_type": "mbart",
       "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 sha256:978121bbec54ae0b7c9589a367951c00ca223d2f7d8b5965fa52d9245e23df76
 size 809287832

 version https://git-lfs.github.com/spec/v1
+oid sha256:f4124e06ab24b422e9914e80b86bbdc30c9c37d4c5edddff1429b4a83739dc58
 size 809287832