diff --git a/README.md b/README.md
new file mode 100644
index 0000000..31bb51a
--- /dev/null
+++ b/README.md
@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: clip-vit-large-patch14-336
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# clip-vit-large-patch14-336
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: None
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.21.3
+- TensorFlow 2.8.2
+- Tokenizers 0.12.1
diff --git a/config.json b/config.json
index 7c3b8b7..e9c5a5d 100644
--- a/config.json
+++ b/config.json
@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "openai/clip-vit-large-patch14-336",
   "architectures": [
     "CLIPModel"
   ],
@@ -59,7 +60,7 @@
     "pad_token_id": 1,
     "prefix": null,
     "problem_type": null,
-    "projection_dim" : 768,
+    "projection_dim": 768,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
@@ -68,6 +69,7 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -75,7 +77,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.18.0.dev0",
+    "transformers_version": "4.21.3",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -134,6 +136,7 @@
     "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_channels": 3,
     "num_hidden_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -143,7 +146,7 @@
     "patch_size": 14,
     "prefix": null,
     "problem_type": null,
-    "projection_dim" : 768,
+    "projection_dim": 768,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
@@ -152,6 +155,7 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -159,7 +163,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.18.0.dev0",
+    "transformers_version": "4.21.3",
     "typical_p": 1.0,
     "use_bfloat16": false
   },
diff --git a/tf_model.h5 b/tf_model.h5
new file mode 100644
index 0000000..b9b9aba
--- /dev/null
+++ b/tf_model.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12828ca8f0f3c92194f277b7d893da7f2fb7824d0b99dedb305eb48eb46bb7f
+size 1712454232