Update tiny models for GroupViTModel

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "GroupViTModel"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "groupvit",
+  "output_segmentation": false,
+  "projection_dim": 64,
+  "projection_intermediate_dim": 4096,
+  "text_config": {
+    "attention_dropout": 0.1,
+    "bos_token_id": 49406,
+    "dropout": 0.1,
+    "eos_token_id": 49407,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 512,
+    "model_type": "groupvit_text_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 49407,
+    "vocab_size": 49408
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "assign_eps": 1.0,
+    "assign_mlp_ratio": [
+      0.5,
+      4
+    ],
+    "attention_dropout": 0.1,
+    "depths": [
+      6,
+      3,
+      3
+    ],
+    "dropout": 0.1,
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-05,
+    "model_type": "groupvit_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_group_tokens": [
+      64,
+      8,
+      0
+    ],
+    "num_hidden_layers": 12,
+    "num_output_groups": [
+      64,
+      8,
+      8
+    ],
+    "patch_size": 2
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c3e4254f4231e979d9fe83de1957fc4f4d7634bc52580a7724b217a517aaab
+size 10333812

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 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 77,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}