Update config.json

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": ".",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -20,7 +21,7 @@
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
     "decoder_layerdrop": 0.0,
-    "decoder_layers": 8,
+    "decoder_layers": 4,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -49,7 +50,7 @@
     },
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 1536,
+    "max_position_embeddings": 3584,
     "min_length": 0,
     "model_type": "mbart",
     "no_repeat_ngram_size": 0,
@@ -123,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      420,
-      420
+      896,
+      672
     ],
     "initializer_range": 0.02,
     "is_decoder": false,
@@ -156,7 +157,6 @@
     "output_scores": false,
     "pad_token_id": null,
     "patch_size": 4,
-    "path_norm": true,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -178,16 +178,14 @@
     "torch_dtype": null,
     "torchscript": false,
     "typical_p": 1.0,
-    "use_2d_embeddings": false,
     "use_absolute_embeddings": false,
     "use_bfloat16": false,
-    "window_size": 5
+    "window_size": 7
   },
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",
   "pad_token_id": 1,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.36.0"
-}
-
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0"
+}