Training in progress, epoch 0

README.md

@@ -1,9 +1,9 @@
 ---
 license: mit
+tags:
+- donut
 datasets:
 - shirastromer/supermarket-receipts
 pipeline_tag: image-to-text
-tags:
-- donut
 ---
 This model is a finetune of the [donut base model](https://huggingface.co/naver-clova-ix/donut-base/)

config.json

@@ -85,9 +85,9 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57556
+    "vocab_size": 57558
   },
-  "decoder_start_token_id": 57555,
+  "decoder_start_token_id": 57557,
   "encoder": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -186,6 +186,7 @@
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",
   "pad_token_id": 1,
+  "task": "<s_cord-v2>",
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a09b8ed25d97b81d21a0555a92124917cb7e33e6cc1cb42489e09ee2c6176e
-size 809197720
+oid sha256:fe301653015527f5706697ad94964afe815bc3a4482b3a0c89beec85900bd993
+size 809205912