annutest
/

somethinglikedonut

Image-Text-to-Text

vision-encoder-decoder

Model card Files Files and versions

annutest commited on Nov 1, 2024

Commit

a4d2b88

·

verified ·

1 Parent(s): 5eb119b

Training in progress, epoch 0

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "annutest/somethinglikedonut",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -85,9 +85,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57540
   },
-  "decoder_start_token_id": 57531,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,

 {
+  "_name_or_path": "naver-clova-ix/donut-base",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
+    "vocab_size": 57532
   },
+  "decoder_start_token_id": 3,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5535089b7b832386ab17d292bda0911393a0557e4e5fd8cf174536f2c35d1a8d
-size 809132184

 version https://git-lfs.github.com/spec/v1
+oid sha256:f307b9a773fbd92213d90159abd0be8d9a43c93d3a5debaeea0b21f3cb7b35cb
+size 809099416