Add text and image encoders with the tokenizer

.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
+clip-vit-base-patch32/clip-vit-base-patch32.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text

clip-vit-base-patch32/clip-vit-base-patch32.aimodel/main.hash

@@ -0,0 +1 @@
+-���B�ڍ�j㡡l��eaSf+��O��

clip-vit-base-patch32/clip-vit-base-patch32.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df20f7fb2ed429eda8d15a96ae3a1a16c9f16e1b6656153662bf8f3a14fbbfa
+size 302697146

clip-vit-base-patch32/clip-vit-base-patch32.aimodel/metadata.json

@@ -0,0 +1,8 @@
+{
+  "author" : "A. Radford et al.",
+  "description" : "CLIP ViT-B\/32 text and image encoders with L2-normalized embeddings. Source: https:\/\/huggingface.co\/openai\/clip-vit-base-patch32",
+  "assetVersion" : "2.0",
+  "creationDate" : "20261025T224506Z",
+  "producer" : "coreai-core 1.0.0b3",
+  "license" : "MIT"
+}

clip-vit-base-patch32/tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

clip-vit-base-patch32/tokenizer/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}