Upload standalone vision decoder: vit-only first commit

open_clip_config.json

@@ -0,0 +1,27 @@
+{
+  "model_cfg": {
+    "embed_dim": 768,
+    "vision_cfg": {
+      "width": 768,
+      "layers": 12,
+      "patch_size": 1,
+      "image_size": 16,
+      "no_ln_pre": true,
+      "pool_type": "avg",
+      "final_ln_after_pool": true,
+      "norm_kwargs": {
+        "eps": 1e-06
+      },
+      "output_tokens": true,
+      "head_width": 64,
+      "in_channels": 768
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 512,
+      "heads": 8,
+      "layers": 12
+    }
+  }
+}

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d533f5f95157903cecc2a9b3d380e8af47de71c7a11867108f8dfbcc15c4bde
+size 345785299