Update tiny models for XCLIPModel

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "XCLIPModel"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "xclip",
+  "projection_dim": 64,
+  "prompt_alpha": 0.1,
+  "prompt_attention_dropout": 0.0,
+  "prompt_hidden_act": "quick_gelu",
+  "prompt_layers": 2,
+  "prompt_num_attention_heads": 4,
+  "prompt_projection_dropout": 0.0,
+  "text_config": {
+    "attention_dropout": 0.1,
+    "bos_token_id": 49406,
+    "dropout": 0.1,
+    "eos_token_id": 49407,
+    "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": "xclip_text_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 49407,
+    "vocab_size": 49408
+  },
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "drop_path_rate": 0.0,
+    "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,
+    "mit_hidden_size": 64,
+    "mit_intermediate_size": 2048,
+    "mit_num_attention_heads": 8,
+    "mit_num_hidden_layers": 1,
+    "model_type": "xclip_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_frames": 8,
+    "num_hidden_layers": 2,
+    "patch_size": 2
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b853383a41e65d01126e16049affea79e5567e288e8c73762256bc9a125a0f25
+size 8139844

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_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}