Upload model

config.json

@@ -86,7 +86,7 @@
   },
   "decoder_start_token_id": 5,
   "encoder": {
-    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "_name_or_path": "encoder",
     "add_cross_attention": false,
     "architectures": [
       "ViTModel"
@@ -115,7 +115,7 @@
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 224,
+    "image_size": 384,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
     "is_decoder": false,
@@ -144,7 +144,7 @@
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
-    "qkv_bias": true,
+    "qkv_bias": false,
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
@@ -159,7 +159,7 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": null,
+    "torch_dtype": "float32",
     "torchscript": false,
     "typical_p": 1.0,
     "use_bfloat16": false

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f039055248c8fad9e3e365371a8c5071f40efb2c0ea8079bdc015f1fd16940
+oid sha256:034ece27a251cf128ec832b57a0c3dd382a4ba9d0124fefeb57e76e094992429
 size 881226788