Upload tiny models for ViTHybridForImageClassification

config.json

@@ -0,0 +1,124 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "ViTHybridForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      3,
+      4,
+      9
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "early_stopping": false,
+    "embedding_dynamic_padding": true,
+    "embedding_size": 64,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "global_padding": "SAME",
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_type": "bottleneck",
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "bit",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_groups": 2,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage1",
+      "stage2",
+      "stage3"
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "output_stride": 32,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3"
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.28.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "width_factor": 1
+  },
+  "backbone_featmap_shape": [
+    1,
+    16,
+    4,
+    4
+  ],
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "image_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit-hybrid",
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 5,
+  "patch_size": 2,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 64,
+    "width": 64
+  },
+  "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": "ViTHybridImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 64
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40792f773ceac0c697cf1fae7a28be6d220cd22de8f4d8139ae83ef7de3d2c5b
+size 323805