Upload ImageTextRetrieval

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "./aa",
+  "architectures": [
+    "ImageTextRetrieval"
+  ],
+  "image_config": {
+    "depths": [
+      3,
+      4,
+      6,
+      3
+    ],
+    "downsample_in_first_stage": false,
+    "embedding_size": 64,
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "image_hidden_act": "relu",
+    "layer_type": "bottleneck",
+    "num_channels": 3,
+    "out_features": null
+  },
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "bert, resnet",
+  "projection_dim": 512,
+  "text_config": {
+    "attention_probs_dropout_prob": 0.1,
+    "classifier_dropout": null,
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "text_hidden_act": "gelu",
+    "type_vocab_size": 2,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7877ed90c0950a5c2067dba14d927e1909b91715807834dd75ed122ebf818567
+size 535761193