Upload VisionTransformer

config.json

@@ -6,14 +6,14 @@
   "attention_implementation": "sdpa",
   "attention_probability_dropout_probability": 0.1,
   "dropout_probability": 0.1,
-  "embedding_size": 512,
+  "embedding_size": 128,
   "hidden_activation_function": "gelu",
-  "hidden_size": 768,
-  "image_size": 288,
+  "hidden_size": 256,
+  "image_size": 224,
   "initializer_factor": 1.0,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 0.01,
-  "num_attention_heads": 12,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "num_attention_heads": 4,
   "num_channels": 3,
   "num_hidden_layers": 12,
   "num_intermediate_layers": 3,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9479fded913273c6151c3dec67a28a69c3b0c6f0c0d477491dea1e3c7e957d58
-size 1705886824
+oid sha256:85fc4c896558392e7fda48f5265b49c77ad2a7014327f78e37a68feb2d5ee622
+size 189997656