Update tiny models for T5Gemma2ForSequenceClassification

.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 +1,177 @@
+{
+  "architectures": [
+    "T5Gemma2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_dropout_rate": 0.0,
+  "decoder": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "cross_attention_hidden_size": 32,
+    "dropout_rate": 0.0,
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 8,
+    "hidden_act": "gelu",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": true,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention"
+    ],
+    "max_position_embeddings": 512,
+    "model_type": "t5gemma2_decoder",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 4096,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 16,
+    "use_cache": true,
+    "vocab_size": 99
+  },
+  "dropout_rate": 0.0,
+  "dtype": "float32",
+  "encoder": {
+    "boi_token_index": 5,
+    "eoi_token_index": 6,
+    "hidden_size": 32,
+    "image_token_index": 4,
+    "initializer_range": 0.02,
+    "mm_tokens_per_image": 2,
+    "model_type": "t5gemma2_encoder",
+    "text_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "attention_probs_dropout_prob": 0.1,
+      "attn_logit_softcapping": null,
+      "bos_token_id": 2,
+      "chunk_size_feed_forward": 0,
+      "dropout_rate": 0.0,
+      "dtype": null,
+      "eos_token_id": 1,
+      "final_logit_softcapping": null,
+      "head_dim": 8,
+      "hidden_act": "gelu",
+      "hidden_activation": "gelu_pytorch_tanh",
+      "hidden_dropout_prob": 0.1,
+      "hidden_size": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 37,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "full_attention",
+        "sliding_attention"
+      ],
+      "max_position_embeddings": 512,
+      "model_type": "t5gemma2_text",
+      "num_attention_heads": 4,
+      "num_hidden_layers": 2,
+      "num_key_value_heads": 2,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": 0,
+      "problem_type": null,
+      "query_pre_attn_scalar": 256,
+      "return_dict": true,
+      "rms_norm_eps": 1e-06,
+      "rope_parameters": {
+        "full_attention": {
+          "rope_theta": 1000000.0,
+          "rope_type": "default"
+        },
+        "sliding_attention": {
+          "rope_theta": 10000.0,
+          "rope_type": "default"
+        }
+      },
+      "sliding_window": 4096,
+      "tie_word_embeddings": true,
+      "type_vocab_size": 16,
+      "use_cache": true,
+      "vocab_size": 99
+    },
+    "tie_word_embeddings": true,
+    "vision_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "chunk_size_feed_forward": 0,
+      "dropout": 0.1,
+      "dtype": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 32,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 20,
+      "initializer_range": 0.02,
+      "intermediate_size": 37,
+      "is_encoder_decoder": false,
+      "is_training": true,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "model_type": "siglip_vision_model",
+      "num_attention_heads": 4,
+      "num_channels": 3,
+      "num_hidden_layers": 2,
+      "num_key_value_heads": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "patch_size": 5,
+      "problem_type": null,
+      "return_dict": true,
+      "use_labels": true
+    }
+  },
+  "eoi_token_index": 6,
+  "eos_token_id": 1,
+  "hidden_size": 32,
+  "image_token_index": 4,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "model_type": "t5gemma2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "vocab_size": 262144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7496db657731f06ebf0b0ad68ee7c8dad992ce16d8f35889c599ce577b2b9f84
+size 231684

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b325224482ec441ec5fbe2a5ac08c3758e0f9605f6e54368e31f736fcfb01d
+size 33384387

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [],
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}