Update tiny models for ModernVBertModel

config.json

@@ -0,0 +1,85 @@
+{
+  "architectures": [
+    "ModernVBertModel"
+  ],
+  "bos_token_id": 50281,
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "dtype": "float32",
+  "eos_token_id": 50282,
+  "image_token_id": 98,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "model_type": "modernvbert",
+  "pad_token_id": 50283,
+  "pixel_shuffle_factor": 2,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.1,
+    "bos_token_id": 50281,
+    "classifier_activation": "gelu",
+    "classifier_bias": false,
+    "classifier_dropout": 0.1,
+    "classifier_pooling": "cls",
+    "cls_token_id": 50281,
+    "decoder_bias": true,
+    "deterministic_flash_attn": false,
+    "embedding_dropout": 0.1,
+    "eos_token_id": 50282,
+    "hidden_activation": "gelu",
+    "hidden_size": 32,
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "is_decoder": false,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention"
+    ],
+    "local_attention": 128,
+    "max_position_embeddings": 512,
+    "mlp_bias": false,
+    "mlp_dropout": 0.1,
+    "model_type": "modernbert",
+    "norm_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "pad_token_id": 50283,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sep_token_id": 50282,
+    "sparse_pred_ignore_index": -100,
+    "sparse_prediction": false,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 2,
+    "vocab_size": 50408
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "dropout": 0.1,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 64,
+    "image_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 4
+  },
+  "vocab_size": 50408
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75de244926111d7a3e4e51bfb8905d920749a7f6bc6ea4770bb8447f1618639
+size 6844392

preprocessor_config.json

@@ -0,0 +1,32 @@
+{
+  "crop_size": {
+    "longest_edge": 16,
+    "shortest_edge": 16
+  },
+  "do_convert_rgb": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Idefics3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_size": {
+    "longest_edge": 364
+  },
+  "resample": 1,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 16,
+    "shortest_edge": 16
+  }
+}

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
+  ],
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask",
+    "pixel_values",
+    "pixel_attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}