Update tiny models for Gemma3nAudioEncoder

.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 +1,48 @@
+{
+  "architectures": [
+    "Gemma3nAudioEncoder"
+  ],
+  "conf_attention_chunk_size": 4,
+  "conf_attention_context_left": 5,
+  "conf_attention_context_right": 0,
+  "conf_attention_logit_cap": 50.0,
+  "conf_conv_kernel_size": 3,
+  "conf_num_attention_heads": 4,
+  "conf_num_hidden_layers": 2,
+  "conf_reduction_factor": 4,
+  "conf_residual_weight": 0.5,
+  "dtype": "float32",
+  "gradient_clipping": 10000000000.0,
+  "hidden_size": 32,
+  "input_feat_size": 32,
+  "model_type": "gemma3n_audio",
+  "rms_norm_eps": 1e-06,
+  "sscp_conv_channel_size": [
+    16,
+    8
+  ],
+  "sscp_conv_group_norm_eps": 0.001,
+  "sscp_conv_kernel_size": [
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      3
+    ]
+  ],
+  "sscp_conv_stride_size": [
+    [
+      2,
+      2
+    ],
+    [
+      2,
+      2
+    ]
+  ],
+  "transformers_version": "5.16.0.dev0",
+  "vocab_offset": 262272,
+  "vocab_size": 262400
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61f5c6c012d690b4e231c16dd3debbcfe2a7b70d428062d69105c90f40cc565
+size 218480

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "Gemma3nAudioFeatureExtractor",
+  "feature_size": 128,
+  "fft_length": 1024,
+  "fft_overdrive": true,
+  "frame_length": 512,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessorFast",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "input_scale_factor": 1.0,
+  "max_frequency": 7600.0,
+  "mel_floor": 1e-05,
+  "min_frequency": 125.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.97,
+  "preemphasis_htk_flavor": true,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_tensors": null,
+  "sampling_rate": 16000,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa40b46d55d1fa5f1c0b218de3a695942c620858ba34aa94e2aa705efc6f071
+size 33442552

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "backend": "tokenizers",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoa_token": "<end_of_audio>",
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<audio_soft_token>",
+    "boa_token": "<start_of_audio>",
+    "boi_token": "<start_of_image>",
+    "eoa_token": "<end_of_audio>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "Gemma3nProcessor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}