Update tiny models for T5GemmaEncoderModel

.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 +1,101 @@
+{
+  "architectures": [
+    "T5GemmaEncoderModel"
+  ],
+  "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": 50.0,
+    "bos_token_id": 2,
+    "cross_attention_hidden_size": 32,
+    "dropout_rate": 0.0,
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "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": [
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 512,
+    "model_type": "t5_gemma_module",
+    "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": {
+      "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": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
+    "attn_logit_softcapping": 50.0,
+    "bos_token_id": 2,
+    "dropout_rate": 0.0,
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "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": false,
+    "layer_types": [
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 512,
+    "model_type": "t5_gemma_module",
+    "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": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "sliding_window": 4096,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 16,
+    "use_cache": true,
+    "vocab_size": 99
+  },
+  "eos_token_id": 1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": false,
+  "model_type": "t5gemma",
+  "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": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3266affd302ea6fb1649511c2c2da8e213d474df9983f6eb31dadce7f020195b
+size 69336

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70d575dcb9d112715587c310734ac9085f24b162585ec589b02389fcbe0561c
+size 34349429

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}