Copy from Letian2003/unified_vit_v66-vision-only

open_clip_config.json

@@ -0,0 +1,27 @@
+{
+  "model_cfg": {
+    "embed_dim": 768,
+    "vision_cfg": {
+      "layers": 12,
+      "width": 768,
+      "patch_size": 2,
+      "image_size": 32,
+      "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": 16
+    },
+    "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 sha256:9d55ca6e9c4bd404dfac552ad65dae673274b28aeffe8f3f00bd7047a1db465e
+size 343622611