Update tiny models for AltCLIPModel

.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 +1,51 @@
+{
+  "architectures": [
+    "AltCLIPModel"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "altclip",
+  "projection_dim": 64,
+  "text_config": {
+    "attention_dropout": 0.1,
+    "attention_probs_dropout_prob": 0,
+    "bos_token_id": 0,
+    "dropout": 0.1,
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "initializer_factor": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 512,
+    "model_type": "altclip_text_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 1,
+    "project_dim": 32,
+    "projection_dim": 32,
+    "type_vocab_size": 1,
+    "vocab_size": 250002
+  },
+  "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": "altclip_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 sha256:4ca3ad61ac9ebb67c807ab2e45f7c8083b197f837c3fc450b9c6eac95073cdf8
+size 32236540

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 sha256:5df1f55d60c9705a501ab9a75550728625740741fe4be308dac4806c16b7d51d
+size 17098085

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "AltCLIPProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}