Add files using upload-large-folder tool

.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

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+base_model: google/gemma-4-E4B-it
+pipeline_tag: image-text-to-text
+library_name: openvino
+tags:
+  - openvino
+  - npu
+  - intel
+  - intel-npu
+  - gemma4
+  - onw
+language:
+  - en
+  - ja
+---
+
+# Gemma 4 E4B-it for onw — every component on the Intel NPU
+
+[google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it) (text + image) packaged for
+**[onw](https://huggingface.co/ryugyosoft/onw)** (俺のNPUがこんなに動くわけない), the engine that runs LLMs entirely
+on the Intel NPU. Same NPU graphs as the standalone
+[ryugyosoft/gemma-4-E4B-it-npu](https://huggingface.co/ryugyosoft/gemma-4-E4B-it-npu), run by the shared engine.
+
+```bash
+hf download ryugyosoft/onw --local-dir onw && cd onw
+start.bat ryugyosoft/gemma-4-E4B-it-onw          # Windows
+bash start.sh ryugyosoft/gemma-4-E4B-it-onw      # Ubuntu
+```
+
+| NPU 3720 (Core Ultra 9 285HX) | |
+|---|---|
+| decode | **6.7-6.8 tok/s** (prompt lookup decoding on, exact) |
+| image + question (284 tokens) | vision 1.9 s + prefill 2.0 s (64-token blocks, >= 24 GB RAM) |
+| follow-up turn | only new tokens are processed (turn 2 of an image chat: 1.7 s vs 4.8 s) |
+| memory | ~8 GB with the 64-token block, ~6 GB without |
+
+What changed vs the standalone repo: the token embedding and the 2.7 GB per-layer embedding table are looked up
+on the host (they are table reads; no NPU worker process any more), the LM head is one shared INT8 input for all
+block sizes, and prompt lookup decoding / prefix reuse come from the engine.
+
+**Download with `hf download` or let `onw` fetch it** — a `git clone` without Git LFS gets pointer files, which
+`onw` detects and reports.
+
+## Files
+
+| file | what |
+|---|---|
+| `seg00_S{1,16,64}.xml` | the static Gemma 4 decoder (head_dim-512 attention split into 256-wide heads, host-built masks) for 1 / 16 / 64-token blocks |
+| `seg01_S*.xml` | LM head + logit softcapping (shared INT8 weight) |
+| `vision.xml` | static vision encoder (280 soft tokens) |
+| `shared.bin` | INT8 token embedding (= tied head), per-layer embedding table + id map |
+| `engine.json`, tokenizer / processor files | metadata for onw |
+
+## License
+
+Apache 2.0, same as the base model. The weights are re-quantized / restructured from it.

chat_template.jinja

@@ -0,0 +1,386 @@
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- 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 not filter_keys or 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['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 == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    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 value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% 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 none -%}
+        {{- 'null' -}}
+    {%- elif 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 -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- 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 %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('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 none -%}
+                    {%- else -%}
+                        {{- raise_exception(
+                            "chat_template: tool_calls[].function.arguments must be a "
+                            "JSON object (mapping), not a string. Deserialize arguments "
+                            "before passing to the template."
+                        ) -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message.get('content') is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item.get('type') == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
+                        {{- '<|image|>' -}}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
+                        {{- '<|audio|>' -}}
+                    {%- elif item.get('type') == 'video' -%}
+                        {{- '<|video|>' -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,198 @@
+{
+  "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": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "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": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "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
+}

engine.json

@@ -0,0 +1,197 @@
+{
+ "arch": "gemma4",
+ "T": 1024,
+ "sizes": [
+  1,
+  16,
+  64
+ ],
+ "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": 2560,
+  "hidden_size_per_layer_input": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_types": [
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "sliding_attention",
+   "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gemma4_text",
+  "moe_intermediate_size": null,
+  "num_attention_heads": 8,
+  "num_experts": null,
+  "num_global_key_value_heads": null,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 2,
+  "num_kv_shared_layers": 18,
+  "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": false,
+  "vocab_size": 262144,
+  "vocab_size_per_layer_input": 262144
+ },
+ "segments": {
+  "seg00_S1.xml": {
+   "index": 0,
+   "consume_moe": null,
+   "router_layer": null,
+   "S": 1,
+   "slots": 0,
+   "head": false
+  },
+  "seg01_S1.xml": {
+   "index": 1,
+   "consume_moe": null,
+   "router_layer": null,
+   "S": 1,
+   "slots": 0,
+   "head": true
+  },
+  "seg00_S16.xml": {
+   "index": 0,
+   "consume_moe": null,
+   "router_layer": null,
+   "S": 16,
+   "slots": 0,
+   "head": false
+  },
+  "seg01_S16.xml": {
+   "index": 1,
+   "consume_moe": null,
+   "router_layer": null,
+   "S": 16,
+   "slots": 0,
+   "head": true
+  },
+  "seg00_S64.xml": {
+   "index": 0,
+   "consume_moe": null,
+   "router_layer": null,
+   "S": 64,
+   "slots": 0,
+   "head": false
+  },
+  "seg01_S64.xml": {
+   "index": 1,
+   "consume_moe": null,
+   "router_layer": null,
+   "S": 64,
+   "slots": 0,
+   "head": true
+  }
+ },
+ "masks": {
+  "sliding_window": 512
+ },
+ "host_inputs": {
+  "per_layer_inputs": {
+   "table": "ple",
+   "shape": [
+    42,
+    256
+   ]
+  }
+ },
+ "vision": {
+  "type": "gemma",
+  "soft_tokens": 280,
+  "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_token_id": 258880,
+  "pad_token_id": 0
+ },
+ "npu_vision_fallback": {
+  "NPU_USE_NPUW": "YES",
+  "NPUW_DEVICES": "NPU",
+  "NPUW_FOLD": "YES"
+ }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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": "5.5.4"
+}

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "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
+}

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"
+  }
+}

seg00_S1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b18a93e134fd55cdcd54772c26b4d966a371c6763eb8ab020e0ce91f87a971
+size 2050670280

seg00_S16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b18a93e134fd55cdcd54772c26b4d966a371c6763eb8ab020e0ce91f87a971
+size 2050670280

seg00_S64.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b18a93e134fd55cdcd54772c26b4d966a371c6763eb8ab020e0ce91f87a971
+size 2050670280

seg01_S1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e48af94438b6e5de715ec5e3e80e252dc3f66d9ea35b3bdb8dac0650fa8ad71
+size 6

seg01_S1.xml

@@ -0,0 +1,256 @@
+<?xml version="1.0"?>
+<net name="gemma4_head_S1" version="11">
+	<layers>
+		<layer id="0" name="carry.h" type="Parameter" version="opset1">
+			<data shape="1,1,2560" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="carry.h">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="shared.head_q" type="Parameter" version="opset1">
+			<data shape="262144,2560" element_type="i8" />
+			<output>
+				<port id="0" precision="I8" names="shared.head_q">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="shared.head_s" type="Parameter" version="opset1">
+			<data shape="262144" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="shared.head_s">
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Convert_27003" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_26988" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="5" name="Multiply_26989" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2560</dim>
+				</port>
+				<port id="1" precision="FP32" />
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Convert_26992" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="Convert_26993" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="MatMul_26994" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>2560</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Convert_26995" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Multiply_26996" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="Tanh_26997" type="Tanh" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Constant_26999_compressed" type="Const" version="opset1">
+			<data element_type="f16" shape="" offset="4" size="2" />
+			<output>
+				<port id="0" precision="FP16" />
+			</output>
+		</layer>
+		<layer id="13" name="Constant_26999" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16" />
+			</input>
+			<output>
+				<port id="1" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="14" name="Multiply_27000" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+				<port id="1" precision="FP32" />
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Multiply_27000.0" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16" names="logits">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Result_27001" type="Result" version="opset1" output_names="logits">
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="9" to-port="0" />
+		<edge from-layer="3" from-port="1" to-layer="5" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="1" />
+		<edge from-layer="5" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="7" to-port="0" />
+		<edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="10" to-port="1" />
+		<edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
+		<edge from-layer="11" from-port="1" to-layer="14" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="13" from-port="1" to-layer="14" to-port="1" />
+		<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="16" to-port="0" />
+	</edges>
+	<rt_info>
+		<info name="OpenVINO Runtime" value="2026.5.0-23160-6db412d0a27" />
+	</rt_info>
+</net>

seg01_S16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e48af94438b6e5de715ec5e3e80e252dc3f66d9ea35b3bdb8dac0650fa8ad71
+size 6

seg01_S16.xml

@@ -0,0 +1,256 @@
+<?xml version="1.0"?>
+<net name="gemma4_head_S16" version="11">
+	<layers>
+		<layer id="0" name="carry.h" type="Parameter" version="opset1">
+			<data shape="1,16,2560" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="carry.h">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="shared.head_q" type="Parameter" version="opset1">
+			<data shape="262144,2560" element_type="i8" />
+			<output>
+				<port id="0" precision="I8" names="shared.head_q">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="shared.head_s" type="Parameter" version="opset1">
+			<data shape="262144" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="shared.head_s">
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Convert_54279" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_54264" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="5" name="Multiply_54265" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>2560</dim>
+				</port>
+				<port id="1" precision="FP32" />
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Convert_54268" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="Convert_54269" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="MatMul_54270" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>2560</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Convert_54271" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Multiply_54272" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="Tanh_54273" type="Tanh" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Constant_54275_compressed" type="Const" version="opset1">
+			<data element_type="f16" shape="" offset="4" size="2" />
+			<output>
+				<port id="0" precision="FP16" />
+			</output>
+		</layer>
+		<layer id="13" name="Constant_54275" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16" />
+			</input>
+			<output>
+				<port id="1" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="14" name="Multiply_54276" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+				<port id="1" precision="FP32" />
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Multiply_54276.0" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16" names="logits">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Result_54277" type="Result" version="opset1" output_names="logits">
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>16</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="9" to-port="0" />
+		<edge from-layer="3" from-port="1" to-layer="5" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="1" />
+		<edge from-layer="5" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="7" to-port="0" />
+		<edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="10" to-port="1" />
+		<edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
+		<edge from-layer="11" from-port="1" to-layer="14" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="13" from-port="1" to-layer="14" to-port="1" />
+		<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="16" to-port="0" />
+	</edges>
+	<rt_info>
+		<info name="OpenVINO Runtime" value="2026.5.0-23160-6db412d0a27" />
+	</rt_info>
+</net>

seg01_S64.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e48af94438b6e5de715ec5e3e80e252dc3f66d9ea35b3bdb8dac0650fa8ad71
+size 6

seg01_S64.xml

@@ -0,0 +1,256 @@
+<?xml version="1.0"?>
+<net name="gemma4_head_S64" version="11">
+	<layers>
+		<layer id="0" name="carry.h" type="Parameter" version="opset1">
+			<data shape="1,64,2560" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="carry.h">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="shared.head_q" type="Parameter" version="opset1">
+			<data shape="262144,2560" element_type="i8" />
+			<output>
+				<port id="0" precision="I8" names="shared.head_q">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="shared.head_s" type="Parameter" version="opset1">
+			<data shape="262144" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="shared.head_s">
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Convert_81368" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_81353" type="Const" version="opset1">
+			<data element_type="f32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="5" name="Multiply_81354" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>2560</dim>
+				</port>
+				<port id="1" precision="FP32" />
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="Convert_81357" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="Convert_81358" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="MatMul_81359" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>2560</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+					<dim>2560</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Convert_81360" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Multiply_81361" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="11" name="Tanh_81362" type="Tanh" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Constant_81364_compressed" type="Const" version="opset1">
+			<data element_type="f16" shape="" offset="4" size="2" />
+			<output>
+				<port id="0" precision="FP16" />
+			</output>
+		</layer>
+		<layer id="13" name="Constant_81364" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16" />
+			</input>
+			<output>
+				<port id="1" precision="FP32" />
+			</output>
+		</layer>
+		<layer id="14" name="Multiply_81365" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+				<port id="1" precision="FP32" />
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Multiply_81365.0" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16" names="logits">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="Result_81366" type="Result" version="opset1" output_names="logits">
+			<input>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>64</dim>
+					<dim>262144</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="9" to-port="0" />
+		<edge from-layer="3" from-port="1" to-layer="5" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="5" to-port="1" />
+		<edge from-layer="5" from-port="2" to-layer="8" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="7" to-port="0" />
+		<edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="10" to-port="1" />
+		<edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
+		<edge from-layer="11" from-port="1" to-layer="14" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="13" from-port="1" to-layer="14" to-port="1" />
+		<edge from-layer="14" from-port="2" to-layer="15" to-port="0" />
+		<edge from-layer="15" from-port="1" to-layer="16" to-port="0" />
+	</edges>
+	<rt_info>
+		<info name="OpenVINO Runtime" value="2026.5.0-23160-6db412d0a27" />
+	</rt_info>
+</net>

shared.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402bac867a19a87a5b21800b3a093bc56306b49e52a7bd5a3a9cdf471a7175c6
+size 3492282368

shared.bin.json

@@ -0,0 +1 @@
+{"tensors": {"embed_q": {"at": [0, 671088640], "type": "i8", "shape": [262144, 2560]}, "embed_s": {"at": [671088640, 524288], "type": "f16", "shape": [262144]}, "head_q": {"alias": "embed_q"}, "head_s": {"at": [671612928, 524288], "type": "f16", "shape": [262144]}, "ple_q": {"at": [672137216, 2818572288], "type": "i8", "shape": [262144, 10752]}, "ple_s": {"at": [3490709504, 524288], "type": "f16", "shape": [262144]}, "ple_map": {"at": [3491233792, 1048576], "type": "i32", "shape": [262144]}}}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

tokenizer_config.json

@@ -0,0 +1,141 @@
+{
+  "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": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
+  "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>"
+}

vision.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7728ad030d97e7ab324ca25e39f587343fda470cf95db97c45fec3035d82980
+size 169812500