Upload 2 files

config.json

@@ -32,17 +32,29 @@
     "use_cache": true,
     "vocab_size": 30522,
     "max_text_length": 100,
-    "vision_config": {
-        "model_type": "tvp_vision_model",
-        "features": ["res5"],
-        "resnets_depth": 50,
-        "resnets_num_groups": 1,
-        "resnets_width_per_group": 64,
-        "resnets_stem_input_channels": 3,
-        "resnets_stem_out_channels": 64,
-        "resnets_res_out_channels": 256,
-        "resnets_res_dilation": 1,
-        "grid_encoder_conv_input_size": 2048,
-        "grid_encoder_conv_output_size": 768
+    "backbone_config": {
+      "architectures": [
+        "ResNetModel"
+      ],
+      "depths": [
+        3,
+        4,
+        6,
+        3
+      ],
+      "downsample_in_first_stage": false,
+      "embedding_size": 64,
+      "hidden_act": "relu",
+      "hidden_sizes": [
+        256,
+        512,
+        1024,
+        2048
+      ],
+      "layer_type": "bottleneck",
+      "model_type": "resnet",
+      "num_channels": 3,
+      "torch_dtype": "float32",
+      "downsample_in_bottleneck": true
     }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466775a111c4ed36422d9d109929ef6324646cdcfd7097f5e9431ae0b74506ed
-size 673774755
+oid sha256:903b5d9843a26e7836bb55cb684342d7de7f9813794af54dc46999592f7fffed
+size 673768937