Update tiny models for Aimv2VisionModel

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "Aimv2VisionModel"
+  ],
+  "attention_dropout": 0.1,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "image_size": 30,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "is_native": false,
+  "mlp_bias": false,
+  "model_type": "aimv2_vision_model",
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 2,
+  "patch_size": 2,
+  "projection_dim": 32,
+  "qkv_bias": false,
+  "rms_norm_eps": 1e-05,
+  "transformers_version": "5.16.0.dev0",
+  "use_head": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a72be2f36c408ef6fd8a9737d6804d27c081dc379b7a4e1a159eeeb910c1867
+size 107672

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "longest_edge": 30,
+    "shortest_edge": 30
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 30,
+    "shortest_edge": 30
+  }
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<start_of_text>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_text>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 77,
+  "pad_token": "<end_of_text>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<end_of_text>",
+  "use_fast": true
+}