Initial model version

config.json

@@ -0,0 +1,15 @@
+{
+  "architectures": [
+    "FLAVACodebook"
+  ],
+  "freeze": null,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "input_channels": 3,
+  "model_type": "flava_codebook",
+  "num_blocks_per_group": 2,
+  "num_groups": 4,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "vocab_size": 8192
+}

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 112,
+  "do_center_crop": true,
+  "do_map_pixels": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "FLAVACodebookFeatureExtractor",
+  "image_mean": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "image_std": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "resample": 1,
+  "size": 112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c4cdf50070bcef317e0d59675bdeb639dec040524b0f9d38982ae32c1e46a4
+size 215167943