Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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
+onnx/audio_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1 @@
+{%- for msg in messages if msg.get('role') == 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- for item in msg['content'] if item.get('type') == 'text' -%}{{ item['text'] }}{%- endfor -%}{%- endif -%}{%- endfor -%}{%- for msg in messages if msg.get('role') != 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- set existing_text = msg['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | join -%}{%- set has_manual_placeholders = ('<|image|>' in existing_text) or ('<|video|>' in existing_text) or ('<|audio|>' in existing_text) -%}{%- for item in msg['content'] -%}{%- if item.get('type') == 'text' -%}{{ item['text'] }}{%- elif not has_manual_placeholders and item.get('type') == 'image' -%}<|image|>{%- elif not has_manual_placeholders and item.get('type') == 'video' -%}<|video|>{%- elif not has_manual_placeholders and item.get('type') == 'audio' -%}<|audio|>{%- endif -%}{%- endfor -%}{%- endif -%}{%- endfor -%}

config.json

@@ -0,0 +1,160 @@
+{
+  "architectures": [
+    "EmbeddingGemma2Model"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "float32",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 48,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      4
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "float32",
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "embedding_gemma2",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 2,
+    "dtype": "float32",
+    "embedding_dim": 24,
+    "eos_token_id": 1,
+    "head_dim": 8,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "hidden_size_per_layer_input": 8,
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "embedding_gemma2_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 6,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "per_layer_config": {
+      "2": {
+        "head_dim": 16,
+        "num_key_value_heads": 1
+      },
+      "5": {
+        "head_dim": 16,
+        "num_key_value_heads": 1
+      }
+    },
+    "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": 4,
+    "vocab_size": 262144
+  },
+  "transformers_version": "5.18.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "float32",
+    "global_head_dim": 16,
+    "head_dim": 16,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 64,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "axial"
+    },
+    "standardize": false,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "audio_encoder.onnx": 1,
+      "model.onnx": 1,
+      "model_fp16.onnx": 1,
+      "vision_encoder.onnx": 1,
+      "vision_encoder_fp16.onnx": 1
+    }
+  }
+}

onnx/audio_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8681851560aa387640bab9895524bc6f0d6d475b53e2f8325c889496985db663
+size 36625

onnx/audio_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d0d9b5747925dbd6b7070cd4e7bd21e714e38dc300679c7d7cbf794483b159
+size 243456

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcf1e719cba8b7d461e386a46499d73647c657d61888b8f0675e3b5b814d961
+size 126772

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c55f4f002901571e59e6277bb8165468e15f96bf9259685e318180bdbe5eaf4
+size 33813504

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dacb7866a0cd81aa7de0aa7b5dec115a8a007209228edf2df9125fbd634eedc
+size 131347

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebeeb49f07aad853e959f05a6364b0f7149d08429a95d5a7fdb67c09c7105ae0
+size 16900608

onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c74608069935eee71993e191e91d2f21a3df65d6e2c8785436f5cb6c43c3f9c
+size 24297

onnx/vision_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b1d752d2b73e7b2c53245158b7bbd90ddb822a2574aba190801aeb22adccd8
+size 2805760

onnx/vision_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9b366c8663ddc8572f29121430977c2ddd34e1337c06e2b845447207ef07bc
+size 23604

onnx/vision_encoder_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8580648207636ddd0b449b53469ccb438481b37077a89b6de5b98beecfb5ee8
+size 1402880

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "dither": 0.0,
+  "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+  "feature_size": 128,
+  "fft_length": 512,
+  "fft_overdrive": false,
+  "frame_length": 320,
+  "hop_length": 160,
+  "input_scale_factor": 1.0,
+  "max_frequency": 8000.0,
+  "mel_floor": 0.001,
+  "min_frequency": 0.0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "per_bin_mean": null,
+  "per_bin_stddev": null,
+  "preemphasis": 0.0,
+  "preemphasis_htk_flavor": true,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "processor_class": "EmbeddingGemma2Processor"
+}

processor_config.json

@@ -0,0 +1,78 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 280,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "EmbeddingGemma2Processor",
+  "video_processor": {
+    "add_timestamps": false,
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 1,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_frames": 32,
+    "max_soft_tokens": 140,
+    "overflow_strategy": "uniform",
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "EmbeddingGemma2VideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4
+size 32170510

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>",
+    "video_token": "<|video|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "EmbeddingGemma2Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "video_token": "<|video|>"
+}