Update tiny models for MgpstrForSceneTextRecognition

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MgpstrForSceneTextRecognition"
+  ],
+  "attn_drop_rate": 0.0,
+  "distilled": false,
+  "drop_path_rate": 0.0,
+  "drop_rate": 0.0,
+  "dtype": "float32",
+  "hidden_size": 32,
+  "image_size": [
+    32,
+    128
+  ],
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "max_token_length": 27,
+  "mlp_ratio": 4.0,
+  "model_type": "mgp-str",
+  "num_attention_heads": 4,
+  "num_bpe_labels": 99,
+  "num_channels": 3,
+  "num_character_labels": 38,
+  "num_hidden_layers": 2,
+  "num_wordpiece_labels": 99,
+  "output_a3_attentions": false,
+  "output_hidden_states": null,
+  "patch_size": 4,
+  "qkv_bias": true,
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe40783dc65f846792bbf6e15b530446d737601c685252d91b09d1e0162eaa7
+size 192312

preprocessor_config.json

@@ -0,0 +1,38 @@
+{
+  "crop_size": {
+    "height": [
+      32,
+      128
+    ],
+    "width": [
+      32,
+      128
+    ]
+  },
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": [
+      32,
+      128
+    ],
+    "width": [
+      32,
+      128
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[GO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[s]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "[GO]",
+  "eos_token": "[s]",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[GO]",
+  "tokenizer_class": "MgpstrTokenizer",
+  "unk_token": "[GO]"
+}

vocab.json

@@ -0,0 +1,40 @@
+{
+  "0": 2,
+  "1": 3,
+  "2": 4,
+  "3": 5,
+  "4": 6,
+  "5": 7,
+  "6": 8,
+  "7": 9,
+  "8": 10,
+  "9": 11,
+  "[GO]": 0,
+  "[s]": 1,
+  "a": 12,
+  "b": 13,
+  "c": 14,
+  "d": 15,
+  "e": 16,
+  "f": 17,
+  "g": 18,
+  "h": 19,
+  "i": 20,
+  "j": 21,
+  "k": 22,
+  "l": 23,
+  "m": 24,
+  "n": 25,
+  "o": 26,
+  "p": 27,
+  "q": 28,
+  "r": 29,
+  "s": 30,
+  "t": 31,
+  "u": 32,
+  "v": 33,
+  "w": 34,
+  "x": 35,
+  "y": 36,
+  "z": 37
+}