Update tiny models for MetaClip2Model

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "MetaClip2Model"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "projection_dim": 64,
+  "text_config": {
+    "attention_dropout": 0.1,
+    "bos_token_id": 0,
+    "dropout": 0.1,
+    "eos_token_id": 2,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 512,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 1,
+    "projection_dim": 32,
+    "vocab_size": 901629
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "dropout": 0.1,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 2,
+    "projection_dim": 32
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474829daae8c044b1d7b3d0aa091273a6e6f854b08595aed242b47630e16d593
+size 115639444

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "longest_edge": 30,
+    "shortest_edge": 30
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 30,
+    "shortest_edge": 30
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef2cc8deb9e37805d5e5393ad945ab60a30963516f8adebfd495629a94176b5
+size 61333815

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "max_length": 77,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "CLIPProcessor",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}