Update tiny models for VisionTextDualEncoderModel-vit-bert

config.json

@@ -0,0 +1,91 @@
+{
+  "architectures": [
+    "VisionTextDualEncoderModel"
+  ],
+  "dtype": "float32",
+  "logit_scale_init_value": 2.6592,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "/tmp/tmplo0207hs/decoder/BertModel",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "return_dict": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 16,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "_name_or_path": "/tmp/tmplo0207hs/encoder/ViTModel",
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "chunk_size_feed_forward": 0,
+    "dtype": "float32",
+    "encoder_stride": 2,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 30,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "model_type": "vit",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 2,
+    "pooler_act": "tanh",
+    "pooler_output_size": 32,
+    "problem_type": null,
+    "qkv_bias": true,
+    "return_dict": true
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f351e91ae0f6940edef0e01bc15937bbbb600053ed0cddedacb216bbe3e474d
+size 4263268

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 30,
+    "width": 30
+  }
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}