update

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+    "_commit_hash": null,
+    "architectures": [
+      "ViTaminCLIP"
+    ],
+    "auto_map": {
+      "AutoConfig": "configuration_vitamin.ViTaminConfig",
+      "AutoModel": "model.ViTaminCLIP"
+    },
+    "embed_dim": 768,
+    "vision_cfg": {
+      "timm_model_name": "vitamin_large_336",
+      "timm_model_pretrained": false,
+      "timm_pool": "",
+      "timm_proj": "linear",
+      "timm_drop": 0.0,
+      "timm_drop_path": 0.1,
+      "image_size": 336
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 768,
+      "heads": 12,
+      "layers": 12
+    }
+}

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+    "crop_size": 336,
+    "do_center_crop": true,
+    "do_normalize": true,
+    "do_resize": true,
+    "feature_extractor_type": "CLIPFeatureExtractor",
+    "image_mean": [
+        0.48145466,
+        0.4578275,
+        0.40821073
+    ],
+    "image_std": [
+        0.26862954,
+        0.26130258,
+        0.27577711
+    ],
+    "resample": 3,
+    "size": 336
+  }
+  

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329e83d3cb82144eb84dd22392554bb1afb345dfcf65f750f99d7dd143a0e9a8
+size 2751728357