Update model

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "AIMv2Model"
+    "Aimv2VisionModel"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
@@ -8,10 +8,14 @@
     "AutoModel": "modeling_aimv2.AIMv2Model",
     "FlaxAutoModel": "modeling_flax_aimv2.FlaxAIMv2Model"
   },
+  "hidden_act": "silu",
   "hidden_size": 1024,
   "image_size": 224,
+  "initializer_range": 0.02,
   "intermediate_size": 2816,
-  "model_type": "aimv2",
+  "is_native": false,
+  "mlp_bias": false,
+  "model_type": "aimv2_vision_model",
   "num_attention_heads": 8,
   "num_channels": 3,
   "num_hidden_layers": 24,
@@ -20,6 +24,7 @@
   "qkv_bias": false,
   "rms_norm_eps": 1e-05,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
-  "use_bias": false
-}
+  "transformers_version": "4.54.0.dev0",
+  "use_bias": false,
+  "use_head": false
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0736a439b17ce0405b52473e25d0b2b482eace1aa2c909160f64a132223ba7e
-size 1236809392
+oid sha256:8ff60adc9c00d936fef310a9f8bffbbc3032aee468976f677711ece79121a715
+size 1236816248

preprocessor_config.json

@@ -3,6 +3,10 @@
     "height": 224,
     "width": 224
   },
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
   "do_center_crop": true,
   "do_convert_rgb": true,
   "do_normalize": true,
@@ -13,14 +17,16 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPImageProcessor",
+  "image_processor_type": "CLIPImageProcessorFast",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
+  "input_data_format": null,
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
   "size": {
     "shortest_edge": 224
   }