Upload model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vikp/order2",
+  "_name_or_path": "vikp/order_hr",
   "architectures": [
     "OrderVisionEncoderDecoderModel"
   ],
@@ -23,7 +23,7 @@
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
     "decoder_layerdrop": 0.0,
-    "decoder_layers": 4,
+    "decoder_layers": 3,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -52,10 +52,11 @@
       "LABEL_1": 1
     },
     "length_penalty": 1.0,
-    "max_height": 1005,
-    "max_length": 256,
+    "max_height": 1285,
+    "max_length": 20,
     "max_position_embeddings": 1536,
-    "max_width": 1005,
+    "max_target_positions": 517,
+    "max_width": 1285,
     "min_length": 0,
     "model_type": "mbart",
     "no_repeat_ngram_size": 0,
@@ -65,7 +66,6 @@
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
-    "output_scale": 1000,
     "output_scores": false,
     "pad_token_id": 1,
     "prefix": null,
@@ -91,7 +91,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57525
+    "vocab_size": 261
   },
   "encoder": {
     "_name_or_path": "vikp/donut-encoder",
@@ -107,10 +107,10 @@
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "depths": [
-      3,
-      4,
+      2,
+      2,
       14,
-      3
+      2
     ],
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -186,14 +186,14 @@
     "torch_dtype": "float32",
     "torchscript": false,
     "typical_p": 1.0,
-    "use_2d_embeddings": true,
-    "use_absolute_embeddings": false,
+    "use_2d_embeddings": false,
+    "use_absolute_embeddings": true,
     "use_bfloat16": false,
     "window_size": 7
   },
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.36.2"
 }

generation_config.json

@@ -3,7 +3,6 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
-  "max_length": 256,
   "pad_token_id": 1,
   "transformers_version": "4.36.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab3677b1d27a835e7f6ca54f719409789a9892f5b56f13b887858fef8415b0b
-size 306486136
+oid sha256:76385baeaf50eab204bbd39b7ee7fb47af2763ff3319a088430f1eecd6776f13
+size 550040752