diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..0cb9a4e534706488d6812d01208b830de4790dcd 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,35 @@ 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/audio_encoder_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/audio_encoder_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/audio_encoder_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/audio_encoder_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data_4 filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_fp16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_fp16.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_quantized.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_fp16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_quantized.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/embed_tokens_quantized.onnx_data_2 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
+onnx/vision_encoder_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..afb1d517bedb410d5bb32df4300d17f6e5888e2a
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,263 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{ bos_token }}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {{- messages[0]['content'] | trim -}}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+        {{- '<|turn>' + role + '\n' }}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['tool_calls'] -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- if message['tool_responses'] -%}
+                {#- Tool Response handling -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- '<|tool_response>' -}}
+                    {%- if tool_response['response'] is mapping -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}
+                        {%- for key, value in tool_response['response'] | dictsort -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- if not loop.last %},{% endif -%}
+                        {%- endfor -%}
+                        {{- '}' -}}
+                    {%- else -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}
+                    {%- endif -%}
+                    {{- '<tool_response|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_response' -%}
+            {%- endif -%}
+
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '\n\n<|image|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '\n\n<|video|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+        {%- if not (message['tool_responses'] and not message['content']) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a7f7623b5229c8498655847bd9cdeea34e5017f6
--- /dev/null
+++ b/config.json
@@ -0,0 +1,210 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "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": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "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": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1536,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 35,
+    "num_key_value_heads": 1,
+    "num_kv_shared_layers": 20,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": true,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0.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": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "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": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "audio_encoder": 1,
+      "vision_encoder": 1,
+      "decoder_model_merged.onnx": 5,
+      "decoder_model_merged_fp16.onnx": 3,
+      "decoder_model_merged_quantized.onnx": 2,
+      "decoder_model_merged_q4.onnx": 1,
+      "decoder_model_merged_q4f16.onnx": 1,
+      "embed_tokens.onnx": 2,
+      "embed_tokens_fp16.onnx": 2,
+      "embed_tokens_quantized.onnx": 3,
+      "embed_tokens_q4.onnx": 1,
+      "embed_tokens_q4f16.onnx": 1
+    },
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    }
+  }
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b2b0ab11eaf5317ad648bb48ce64b110532d661a
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0.dev0",
+  "trust_remote_code": false
+}
diff --git a/onnx/audio_encoder.onnx b/onnx/audio_encoder.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..5a6a93f06f1ec72e102451e33c6b5bb60f8b16ee
--- /dev/null
+++ b/onnx/audio_encoder.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e8bdf202be608abe55ed3f1f180b897a73387b5c76f8801c9023c6dbc525b0
+size 220280
diff --git a/onnx/audio_encoder.onnx_data b/onnx/audio_encoder.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..114cf5ce5997bdbff6cbca049b001c09461be4c5
--- /dev/null
+++ b/onnx/audio_encoder.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9fc0d5a06df02638d681ce15c51b84ba94fa7824e0e25effbeba4f02b9ba3c
+size 1179042304
diff --git a/onnx/audio_encoder_fp16.onnx b/onnx/audio_encoder_fp16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..e00e3d2dc161b1996425d4c7c63c4a35110ff34a
--- /dev/null
+++ b/onnx/audio_encoder_fp16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40fa9ce8da3996822d064762ffcbac24f44721e72f62d870dbd66619099ebf9
+size 219310
diff --git a/onnx/audio_encoder_fp16.onnx_data b/onnx/audio_encoder_fp16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..260b2ef2eddd1f96c678ce227e6837dd8e1f312d
--- /dev/null
+++ b/onnx/audio_encoder_fp16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb81ececc02d80405b8455f3f6206daedfcf1f3ea3f3286d838a62f83747f931
+size 589840640
diff --git a/onnx/audio_encoder_q4.onnx b/onnx/audio_encoder_q4.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..412b17e1338fbc3cc2b7091a91ffcfe35767c092
--- /dev/null
+++ b/onnx/audio_encoder_q4.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a1d1f7821ef93809155448e4e441aadf14a4a159da5e6ce9ca7468f80b44dc
+size 261229
diff --git a/onnx/audio_encoder_q4.onnx_data b/onnx/audio_encoder_q4.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..346b165646bc8b44d8bd2e094da66b806e0d57ed
--- /dev/null
+++ b/onnx/audio_encoder_q4.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae533f4fd4103b2f76b0d60082bf0de8567c2225d65dfe34461662b20d4da320
+size 190083584
diff --git a/onnx/audio_encoder_q4f16.onnx b/onnx/audio_encoder_q4f16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..1a1d19d72bf23bc787c67dee5c26ef4a5d71eb7a
--- /dev/null
+++ b/onnx/audio_encoder_q4f16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0deb22791685c792d4b8e089deef9670fa4a4cecde434213d6a742e58fc3fa
+size 260446
diff --git a/onnx/audio_encoder_q4f16.onnx_data b/onnx/audio_encoder_q4f16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..3c76e4d7cc2e6524c583241e74198c6b9ae20d9a
--- /dev/null
+++ b/onnx/audio_encoder_q4f16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df58e61a00bafa9449ee5fd52895ce952f158bbdd1fe38df8a68f48f36842e62
+size 171258112
diff --git a/onnx/audio_encoder_quantized.onnx b/onnx/audio_encoder_quantized.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..3d176c274f6b2b95c4c91be114e9c87e59703862
--- /dev/null
+++ b/onnx/audio_encoder_quantized.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12a5f8c5db8cd7be763453657b74f458cb591a03cfeb9b9ebc941db182525f0
+size 265016
diff --git a/onnx/audio_encoder_quantized.onnx_data b/onnx/audio_encoder_quantized.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..57794a5927d78a73f532b252ea5e9c21c0ec057d
--- /dev/null
+++ b/onnx/audio_encoder_quantized.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33257b54b4bc8f84b873244a649be6aa90847e121bfaa648227081a7f55cc4ae
+size 341877248
diff --git a/onnx/decoder_model_merged.onnx b/onnx/decoder_model_merged.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..4686f677f8c03fe5d3e63666d31ea774b13211b1
--- /dev/null
+++ b/onnx/decoder_model_merged.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f0448a61b944293f327f0a8742a2d47f226627fffc62084d34010f6e068c49
+size 524763
diff --git a/onnx/decoder_model_merged.onnx_data b/onnx/decoder_model_merged.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..52783542a9eb190650a77189e8e2b1028b4581df
--- /dev/null
+++ b/onnx/decoder_model_merged.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3014f451f610db57a094d1dd67a54b6a5480608ec93bb2273932374bc1cb811f
+size 2065537024
diff --git a/onnx/decoder_model_merged.onnx_data_1 b/onnx/decoder_model_merged.onnx_data_1
new file mode 100644
index 0000000000000000000000000000000000000000..2cc82591580f00625a890206f8f7142626e139de
--- /dev/null
+++ b/onnx/decoder_model_merged.onnx_data_1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cadb0ea679d5ca07a1e1d509bc640edad9776ac793a4faa3eae4c45c214be25
+size 1972701184
diff --git a/onnx/decoder_model_merged.onnx_data_2 b/onnx/decoder_model_merged.onnx_data_2
new file mode 100644
index 0000000000000000000000000000000000000000..344875169bbb4e01f90047020db2f4d41bcff5bd
--- /dev/null
+++ b/onnx/decoder_model_merged.onnx_data_2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a949dd5fa1b8477af8871809117d55143f5e693c874e9cc05b452104b92907
+size 2063852544
diff --git a/onnx/decoder_model_merged.onnx_data_3 b/onnx/decoder_model_merged.onnx_data_3
new file mode 100644
index 0000000000000000000000000000000000000000..82f18b403ee7dbe85278848cee91a5c1184ae368
--- /dev/null
+++ b/onnx/decoder_model_merged.onnx_data_3
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fa5ec36406f5240a9316847ab8b81ddc8f445b8a2f2cf19024890546660a31
+size 1809004544
diff --git a/onnx/decoder_model_merged.onnx_data_4 b/onnx/decoder_model_merged.onnx_data_4
new file mode 100644
index 0000000000000000000000000000000000000000..dbd40101545e09f3fb15fdbea504acefa3a13c37
--- /dev/null
+++ b/onnx/decoder_model_merged.onnx_data_4
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ac4dec680d3a0a0e936f6ae1f95345f6e9fe3f18667595df870abdeb7da776
+size 1610612736
diff --git a/onnx/decoder_model_merged_fp16.onnx b/onnx/decoder_model_merged_fp16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..e2bc666ec0007456598ab0ebf93623fe24b9da74
--- /dev/null
+++ b/onnx/decoder_model_merged_fp16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34e54181a58d4896c60773ccdb2833ba963114953b7cc0685b34f1c91321e4d4
+size 549636
diff --git a/onnx/decoder_model_merged_fp16.onnx_data b/onnx/decoder_model_merged_fp16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..71a42f7f7d605d7e6d065fd53fb77ac7ea3da4af
--- /dev/null
+++ b/onnx/decoder_model_merged_fp16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072088206a214a434615401ce4da3c524fab05e100b716d5e7d5a58164a366ab
+size 2094595072
diff --git a/onnx/decoder_model_merged_fp16.onnx_data_1 b/onnx/decoder_model_merged_fp16.onnx_data_1
new file mode 100644
index 0000000000000000000000000000000000000000..ec74c31d79709dbf72a2ff3301cdf08f4f424e74
--- /dev/null
+++ b/onnx/decoder_model_merged_fp16.onnx_data_1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccc497a2f29a82b47b3566038e020a3ce10ce5026aa2cb83550e90f4b54c8f4
+size 1860925440
diff --git a/onnx/decoder_model_merged_fp16.onnx_data_2 b/onnx/decoder_model_merged_fp16.onnx_data_2
new file mode 100644
index 0000000000000000000000000000000000000000..59512058112e7493cbe978c048a6fc76b60216c7
--- /dev/null
+++ b/onnx/decoder_model_merged_fp16.onnx_data_2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35317efd0a159769d6499c327742121a4bc13767b1b3725cfe21a9ab75a430a
+size 805306368
diff --git a/onnx/decoder_model_merged_q4.onnx b/onnx/decoder_model_merged_q4.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..f0f1894024ebe5df79a8d10c7c3c0d3cd282bfdb
--- /dev/null
+++ b/onnx/decoder_model_merged_q4.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6edb929bf342c524728d37efd400285ee71525e8fe64ff996341f78c3e577d2
+size 647599
diff --git a/onnx/decoder_model_merged_q4.onnx_data b/onnx/decoder_model_merged_q4.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..b8a20d0bdc401a1c973e80117bc1545bcbf89cb4
--- /dev/null
+++ b/onnx/decoder_model_merged_q4.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b879fe4b946c9b9ff6acb60f7c5eda3d2c9c4df8625895feb2d1e269002f0345
+size 1864102912
diff --git a/onnx/decoder_model_merged_q4f16.onnx b/onnx/decoder_model_merged_q4f16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..7adc582aa61c3e48cc7ce273d5da80043076fb1a
--- /dev/null
+++ b/onnx/decoder_model_merged_q4f16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c0f1fe04f9a3a048fb3319c0671b6cf0346bf33a3a8624c853bcffe01c24a4
+size 673231
diff --git a/onnx/decoder_model_merged_q4f16.onnx_data b/onnx/decoder_model_merged_q4f16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..60066fedf33c0457b82a7dbef4f16ec57f46f676
--- /dev/null
+++ b/onnx/decoder_model_merged_q4f16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b27245a7396cb7039a4e4118bd2a8aa35106bae381522edf7c4867b5f22bb10
+size 1519700992
diff --git a/onnx/decoder_model_merged_quantized.onnx b/onnx/decoder_model_merged_quantized.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..444b46aeef86472f31f014580517432ba18f9326
--- /dev/null
+++ b/onnx/decoder_model_merged_quantized.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3bad4d5330dd3ed1bd588907754c393004114ac4c4f14eac7f228f2d9705ad
+size 654818
diff --git a/onnx/decoder_model_merged_quantized.onnx_data b/onnx/decoder_model_merged_quantized.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..95489f460dc995964e604a698d2c0d82cb1bd504
--- /dev/null
+++ b/onnx/decoder_model_merged_quantized.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e04502814af3a6086397aa2eff45abc1b564df2eca6a9be049a00f82c1745d2
+size 2094681088
diff --git a/onnx/decoder_model_merged_quantized.onnx_data_1 b/onnx/decoder_model_merged_quantized.onnx_data_1
new file mode 100644
index 0000000000000000000000000000000000000000..801cc0dfa4829fa96beae517981cc4bb04475cf8
--- /dev/null
+++ b/onnx/decoder_model_merged_quantized.onnx_data_1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc09f165ded30fe1e48cd8997f2db7e8f0ebadb1108fa9b1b51201d86a04535
+size 944775168
diff --git a/onnx/embed_tokens.onnx b/onnx/embed_tokens.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..b99263b46b991ec4e1c8ec2999f60ef3a0a9b0fe
--- /dev/null
+++ b/onnx/embed_tokens.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93840f00078b7f22ae3302ca15643d363059214e8a9e32ddd38dce1a6cfa6ece
+size 4243
diff --git a/onnx/embed_tokens.onnx_data b/onnx/embed_tokens.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..9776a6456064228179dd6993fb3401ab4f4acdfb
--- /dev/null
+++ b/onnx/embed_tokens.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9d41b71f0b15c47807d3874db443daf67ade7d9750c361c00fcab95ac508c0
+size 1610612736
diff --git a/onnx/embed_tokens.onnx_data_1 b/onnx/embed_tokens.onnx_data_1
new file mode 100644
index 0000000000000000000000000000000000000000..d9f0b3fc3ffbc4ef2b44d075be78657e5fd80760
--- /dev/null
+++ b/onnx/embed_tokens.onnx_data_1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd460a24efb42f32cd4c15a2a4ab6e596bb64399b589508960217b3d6d6ba9c3
+size 9395240960
diff --git a/onnx/embed_tokens_fp16.onnx b/onnx/embed_tokens_fp16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..05e0a4e530620143b4cabeca483b1d5fc4599f2d
--- /dev/null
+++ b/onnx/embed_tokens_fp16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf75108f796accccd4756724f331acac6f464d656d5c0cf1766e9305772abdc
+size 4713
diff --git a/onnx/embed_tokens_fp16.onnx_data b/onnx/embed_tokens_fp16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..24f8c45edc4e9b8447e8523751942a1ac00dbf23
--- /dev/null
+++ b/onnx/embed_tokens_fp16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6055646b44b9eca25abe2941612b1f104d56dd2f9b8b54776e328e351d4fd7
+size 805306368
diff --git a/onnx/embed_tokens_fp16.onnx_data_1 b/onnx/embed_tokens_fp16.onnx_data_1
new file mode 100644
index 0000000000000000000000000000000000000000..8e35ab3f9e69d7f7e59f1156b40044e14af027fb
--- /dev/null
+++ b/onnx/embed_tokens_fp16.onnx_data_1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7bf38285e3f007b5d28c3cd4d81e0b8f69c2534a53d25fb2952ab9b17b48ca
+size 4697620480
diff --git a/onnx/embed_tokens_q4.onnx b/onnx/embed_tokens_q4.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..9e1626c51f8eb67484b81246ca86c7e7a97e6c03
--- /dev/null
+++ b/onnx/embed_tokens_q4.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8c8a2bcc30e8ded7f636967c2a58a346116583356dd933720b005fc88079c4
+size 5142
diff --git a/onnx/embed_tokens_q4.onnx_data b/onnx/embed_tokens_q4.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..4a9f2576309dd5c8773d4f86317c0665f2541965
--- /dev/null
+++ b/onnx/embed_tokens_q4.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40fa957d9988b8a0160c8b0eb5c3f781a237627e9f7153f30514a4ffb2e62888
+size 1762656256
diff --git a/onnx/embed_tokens_q4f16.onnx b/onnx/embed_tokens_q4f16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..9a21220623b4686d5296e5b9b290861f08540a50
--- /dev/null
+++ b/onnx/embed_tokens_q4f16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ca53f6a169471b5699b2f57ee4c7aa2c73732b0152f3909e64b71384444825
+size 5621
diff --git a/onnx/embed_tokens_q4f16.onnx_data b/onnx/embed_tokens_q4f16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..c8226442549810cfceccfa4ba8d48165044db38d
--- /dev/null
+++ b/onnx/embed_tokens_q4f16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024b199e6358ed42970f807686add5f9430d7e254ca7ce22fc9c83f015b9c517
+size 1590689792
diff --git a/onnx/embed_tokens_quantized.onnx b/onnx/embed_tokens_quantized.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..9b8caad5445902045daf3d5619b473542229b679
--- /dev/null
+++ b/onnx/embed_tokens_quantized.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06511401d70359582048796351c894adbd452471f2815b0198b93100e82b37e8
+size 5174
diff --git a/onnx/embed_tokens_quantized.onnx_data b/onnx/embed_tokens_quantized.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..1befc79ac512ef4bc0cd65cd1afa50937849150c
--- /dev/null
+++ b/onnx/embed_tokens_quantized.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea1f5dd855f51b685aeeee967481467c148a41ebdd733d58856b407945b46a3
+size 465567744
diff --git a/onnx/embed_tokens_quantized.onnx_data_1 b/onnx/embed_tokens_quantized.onnx_data_1
new file mode 100644
index 0000000000000000000000000000000000000000..a896f815bd8b8c94b30e01c4df4f86e31ff4bba0
--- /dev/null
+++ b/onnx/embed_tokens_quantized.onnx_data_1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143ff6a1eea191af79be401378bf8970d56ebde33daa6445a156e28acf6a7bc9
+size 2348810240
diff --git a/onnx/embed_tokens_quantized.onnx_data_2 b/onnx/embed_tokens_quantized.onnx_data_2
new file mode 100644
index 0000000000000000000000000000000000000000..39f77572a9046f2b2fcd5a2936f22c5818635553
--- /dev/null
+++ b/onnx/embed_tokens_quantized.onnx_data_2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90b413e9bde49f74c6634e7516b8b3980e207c979ee8af075f342cc1f3eecbe
+size 367001600
diff --git a/onnx/vision_encoder.onnx b/onnx/vision_encoder.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..d3bb3beb8e110e498c6ab70f05182d80f78a4cef
--- /dev/null
+++ b/onnx/vision_encoder.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34fd8510310ae330704c5b3d1571e6a8faa419cd5cd5d709a230fddc366310d
+size 161900
diff --git a/onnx/vision_encoder.onnx_data b/onnx/vision_encoder.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..f39ba0180832163df2bdda5d71930ad5e3f98fb7
--- /dev/null
+++ b/onnx/vision_encoder.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0468ff0c7994459072f712da835eada7a9a8eb21f92ca561ab61570ed3ef15b
+size 674174144
diff --git a/onnx/vision_encoder_fp16.onnx b/onnx/vision_encoder_fp16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..3d8917f4bd400e2d359f478116bef1ac205f8726
--- /dev/null
+++ b/onnx/vision_encoder_fp16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8a95ce26015f10bf7249c2f36ab593fa630bd8b9fd9cb4deb6c308a7e75712
+size 150672
diff --git a/onnx/vision_encoder_fp16.onnx_data b/onnx/vision_encoder_fp16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..be629095d3002cc5aac6badd7d02ef8f3d139acd
--- /dev/null
+++ b/onnx/vision_encoder_fp16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c968a2928b5087f6f5e3628fee436088ad5bfbc5d79d97410322c40aab0b867
+size 337088192
diff --git a/onnx/vision_encoder_q4.onnx b/onnx/vision_encoder_q4.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..a8928248a2d75ada8f6e391717eb5cdb3edfc4a1
--- /dev/null
+++ b/onnx/vision_encoder_q4.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc90fb094fca9ea9aec7f2ef069e37ee01cb3b454f571bf46843e056b951182
+size 200072
diff --git a/onnx/vision_encoder_q4.onnx_data b/onnx/vision_encoder_q4.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..62e3cd72ccdf14bcf624828dd25d8d3ac6af78f8
--- /dev/null
+++ b/onnx/vision_encoder_q4.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df747f790d1f7f451227124388fef863f09d4fb5a6f7e5052472a4f407cc23b9
+size 112105664
diff --git a/onnx/vision_encoder_q4f16.onnx b/onnx/vision_encoder_q4f16.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..fb8bdb1a027b4157a5de4abff2fd4e02fb7c8b8b
--- /dev/null
+++ b/onnx/vision_encoder_q4f16.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a4e48e519ade4eeddbb4cdadb812a7251aea871f7fb5f50576615fd3af22a3
+size 189124
diff --git a/onnx/vision_encoder_q4f16.onnx_data b/onnx/vision_encoder_q4f16.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..3e5a288365720812e5a50c76ae1fd62f1805f506
--- /dev/null
+++ b/onnx/vision_encoder_q4f16.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0835071d2c79c105f8e1b549b7f8dd8c9af07fa95f01ead2e7add280602d3c6d
+size 99189440
diff --git a/onnx/vision_encoder_quantized.onnx b/onnx/vision_encoder_quantized.onnx
new file mode 100644
index 0000000000000000000000000000000000000000..68f0ea369a663ecfd75567369059376ce73fe279
--- /dev/null
+++ b/onnx/vision_encoder_quantized.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae62d0e57f2b665f3e3ba5d0312337eac9860f69e14de88bfdf2e17fa52a8ea
+size 203173
diff --git a/onnx/vision_encoder_quantized.onnx_data b/onnx/vision_encoder_quantized.onnx_data
new file mode 100644
index 0000000000000000000000000000000000000000..d21386ea6797b71c1e778a61e5741cc8587fa9d5
--- /dev/null
+++ b/onnx/vision_encoder_quantized.onnx_data
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea7a1a2eb1f800621ab6772540af3d6988743cb475475c3df086e00389ca707
+size 198376640
diff --git a/preprocessor_config.json b/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..6418e09c5fdb500f7ad9e86a7de9de7e60317f34
--- /dev/null
+++ b/preprocessor_config.json
@@ -0,0 +1,3 @@
+{
+  "processor_class": "Gemma4Processor"
+}
diff --git a/processor_config.json b/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5465974d23e1eca2c46c2809b26c997946ce0d90
--- /dev/null
+++ b/processor_config.json
@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "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": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..d781f9b567efe2d2c999ec37ba3ff3a505838c60
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bd35616c7c782aaca6ccf48c75f3461d5877170984b8836b375107d0a9f566
+size 19439251
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..cdac68ad7864b31ecf321916b7f7cb5149e6aeee
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,96 @@
+{
+  "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": 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|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string",
+        "x-regex": "<\\|channel\\>(?:thought\\n)?(.+?)<channel\\|>"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "type": "string",
+                  "x-mapping-regex": {
+                    "(\\{|,)\\s*([a-zA-Z_]\\w+):": "\\1\"\\2\":",
+                    "<\\|\\\"\\|>": "\""
+                  },
+                  "x-regex": "call:[^{]+(\\{.*\\})"
+                },
+                "name": {
+                  "type": "string",
+                  "x-regex": "call:([^{]+)"
+                }
+              },
+              "type": "object"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call\\>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object"
+  },
+  "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>",
+  "chat_template": "{%- macro format_parameters(properties, required) -%}\n    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n    {%- set ns = namespace(found_first=false) -%}\n    {%- for key, value in properties | dictsort -%}\n        {%- set add_comma = false -%}\n        {%- if key not in standard_keys -%}\n            {%- if ns.found_first %},{% endif -%}\n            {%- set ns.found_first = true -%}\n            {{ key }}:{\n            {%- if value['description'] -%}\n                description:<|\"|>{{ value['description'] }}<|\"|>\n                {%- set add_comma = true -%}\n            {%- endif -%}\n            {%- if value['nullable'] %}\n                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                nullable:true\n            {%- endif -%}\n            {%- if value['type'] | upper == 'STRING' -%}\n                {%- if value['enum'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    enum:{{ format_argument(value['enum']) }}\n                {%- endif -%}\n            {%- elif value['type'] | upper == 'OBJECT' -%}\n                ,properties:{\n                {%- if value['properties'] is defined and value['properties'] is mapping -%}\n                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n                {%- elif value is mapping -%}\n                    {{- format_parameters(value, value['required'] | default([])) -}}\n                {%- endif -%}\n                }\n                {%- if value['required'] -%}\n                    ,required:[\n                    {%- for item in value['required'] | default([]) -%}\n                        <|\"|>{{- item -}}<|\"|>\n                        {%- if not loop.last %},{% endif -%}\n                    {%- endfor -%}\n                    ]\n                {%- endif -%}\n            {%- elif value['type'] | upper == 'ARRAY' -%}\n                {%- if value['items'] is mapping and value['items'] -%}\n                    ,items:{\n                    {%- set ns_items = namespace(found_first=false) -%}\n                    {%- for item_key, item_value in value['items'] | dictsort -%}\n                        {%- if item_value is not none -%}\n                            {%- if ns_items.found_first %},{% endif -%}\n                            {%- set ns_items.found_first = true -%}\n                            {%- if item_key == 'properties' -%}\n                                properties:{\n                                {%- if item_value is mapping -%}\n                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n                                {%- endif -%}\n                                }\n                            {%- elif item_key == 'required' -%}\n                                required:[\n                                {%- for req_item in item_value -%}\n                                    <|\"|>{{- req_item -}}<|\"|>\n                                    {%- if not loop.last %},{% endif -%}\n                                {%- endfor -%}\n                                ]\n                            {%- elif item_key == 'type' -%}\n                                {%- if item_value is string -%}\n                                    type:{{ format_argument(item_value | upper) }}\n                                {%- else -%}\n                                    type:{{ format_argument(item_value | map('upper') | list) }}\n                                {%- endif -%}\n                            {%- else -%}\n                                {{ item_key }}:{{ format_argument(item_value) }}\n                            {%- endif -%}\n                        {%- endif -%}\n                    {%- endfor -%}\n                    }\n                {%- endif -%}\n            {%- endif -%}\n            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n            type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n        {%- endif -%}\n    {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n    declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n    {%- set params = tool_data['function']['parameters'] -%}\n    {%- if params -%}\n        ,parameters:{\n        {%- if params['properties'] -%}\n            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n        {%- endif -%}\n        {%- if params['required'] -%}\n            required:[\n            {%- for item in params['required'] -%}\n                <|\"|>{{- item -}}<|\"|>\n                {{- ',' if not loop.last -}}\n            {%- endfor -%}\n            ],\n        {%- endif -%}\n        {%- if params['type'] -%}\n            type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n        {%- endif -%}\n    {%- endif -%}\n    {%- if 'response' in tool_data['function'] -%}\n        {%- set response_declaration = tool_data['function']['response'] -%}\n        ,response:{\n        {%- if response_declaration['description'] -%}\n            description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n        {%- endif -%}\n        {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n            type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n        {%- endif -%}\n    {%- endif -%}\n    }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n    {%- if argument is string -%}\n        {{- '<|\"|>' + argument + '<|\"|>' -}}\n    {%- elif argument is boolean -%}\n        {{- 'true' if argument else 'false' -}}\n    {%- elif argument is mapping -%}\n        {{- '{' -}}\n        {%- set ns = namespace(found_first=false) -%}\n        {%- for key, value in argument | dictsort -%}\n            {%- if ns.found_first %},{% endif -%}\n            {%- set ns.found_first = true -%}\n            {%- if escape_keys -%}\n                {{- '<|\"|>' + key + '<|\"|>' -}}\n            {%- else -%}\n                {{- key -}}\n            {%- endif -%}\n            :{{- format_argument(value, escape_keys=escape_keys) -}}\n        {%- endfor -%}\n        {{- '}' -}}\n    {%- elif argument is sequence -%}\n        {{- '[' -}}\n        {%- for item in argument -%}\n            {{- format_argument(item, escape_keys=escape_keys) -}}\n            {%- if not loop.last %},{% endif -%}\n        {%- endfor -%}\n        {{- ']' -}}\n    {%- else -%}\n        {{- argument -}}\n    {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n    {%- set ns = namespace(result='') -%}\n    {%- for part in text.split('<channel|>') -%}\n        {%- if '<|channel>' in part -%}\n            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n        {%- else -%}\n            {%- set ns.result = ns.result + part -%}\n        {%- endif -%}\n    {%- endfor -%}\n    {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{ bos_token }}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n    {{- '<|turn>system\\n' -}}\n\n    {#- Inject Thinking token at the very top of the FIRST system turn -#}\n    {%- if enable_thinking is defined and enable_thinking -%}\n        {{- '<|think|>' -}}\n        {%- set ns.prev_message_type = 'think' -%}\n    {%- endif -%}\n\n    {%- if messages[0]['role'] in ['system', 'developer'] -%}\n        {{- messages[0]['content'] | trim -}}\n        {%- set loop_messages = messages[1:] -%}\n    {%- endif -%}\n\n    {%- if tools -%}\n        {%- for tool in tools %}\n            {{- '<|tool>' -}}\n            {{- format_function_declaration(tool) | trim -}}\n            {{- '<tool|>' -}}\n        {%- endfor %}\n        {%- set ns.prev_message_type = 'tool' -%}\n    {%- endif -%}\n\n    {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n    {%- set ns.prev_message_type = None -%}\n    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n        {{- '<|turn>' + role + '\\n' }}\n\n            {%- if message['tool_calls'] -%}\n                {%- for tool_call in message['tool_calls'] -%}\n                    {%- set function = tool_call['function'] -%}\n                    {{- '<|tool_call>call:' + function['name'] + '{' -}}\n                    {%- if function['arguments'] is mapping -%}\n                        {%- set ns_args = namespace(found_first=false) -%}\n                        {%- for key, value in function['arguments'] | dictsort -%}\n                            {%- if ns_args.found_first %},{% endif -%}\n                            {%- set ns_args.found_first = true -%}\n                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n                        {%- endfor -%}\n                    {%- elif function['arguments'] is string -%}\n                        {{- function['arguments'] -}}\n                    {%- endif -%}\n                    {{- '}<tool_call|>' -}}\n                {%- endfor -%}\n                {%- set ns.prev_message_type = 'tool_call' -%}\n            {%- endif -%}\n\n            {%- if message['tool_responses'] -%}\n                {#- Tool Response handling -#}\n                {%- for tool_response in message['tool_responses'] -%}\n                    {{- '<|tool_response>' -}}\n                    {%- if tool_response['response'] is mapping -%}\n                        {{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}\n                        {%- for key, value in tool_response['response'] | dictsort -%}\n                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n                            {%- if not loop.last %},{% endif -%}\n                        {%- endfor -%}\n                        {{- '}' -}}\n                    {%- else -%}\n                        {{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}\n                    {%- endif -%}\n                    {{- '<tool_response|>' -}}\n                {%- endfor -%}\n                {%- set ns.prev_message_type = 'tool_response' -%}\n            {%- endif -%}\n\n            {%- if message['content'] is string -%}\n                {%- if role == 'model' -%}\n                    {{- strip_thinking(message['content']) -}}\n                {%- else -%}\n                    {{- message['content'] | trim -}}\n                {%- endif -%}\n            {%- elif message['content'] is sequence -%}\n                {%- for item in message['content'] -%}\n                    {%- if item['type'] == 'text' -%}\n                        {%- if role == 'model' -%}\n                            {{- strip_thinking(item['text']) -}}\n                        {%- else -%}\n                            {{- item['text'] | trim -}}\n                        {%- endif -%}\n                    {%- elif item['type'] == 'image' -%}\n                        {{- '\\n\\n<|image|>\\n\\n' -}}\n                        {%- set ns.prev_message_type = 'image' -%}\n                    {%- elif item['type'] == 'audio' -%}\n                        {{- '<|audio|>' -}}\n                        {%- set ns.prev_message_type = 'audio' -%}\n                    {%- elif item['type'] == 'video' -%}\n                        {{- '\\n\\n<|video|>\\n\\n' -}}\n                        {%- set ns.prev_message_type = 'video' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n\n        {%- if not (message['tool_responses'] and not message['content']) -%}\n            {{- '<turn|>\\n' -}}\n        {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n    {%- if ns.prev_message_type != 'tool_response' -%}\n        {{- '<|turn>model\\n' -}}\n    {%- endif -%}\n{%- endif -%}"
+}
\ No newline at end of file