Add OpenVINO EPContext models (ORT-loadable compiled OV graph) for gemma-4-E2B-it

openvino-epcontext/audio_encoder/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87362b0e67ce8f4a00d067722c5212725cf0917e3773055151ea712a96d48152
+size 177924108

openvino-epcontext/audio_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235ecd4205512045f38105cecd2c063752b4d06659461e6a0249a3722b0f959f
+size 768

openvino-epcontext/audio_feature_extraction.json

@@ -0,0 +1,30 @@
+{
+    "feature_extraction": {
+        "sequence": [
+            {
+                "operation": {
+                    "name": "audio_decoder",
+                    "type": "AudioDecoder"
+                }
+            },
+            {
+                "operation": {
+                    "name": "gemma4_log_mel",
+                    "type": "Gemma4LogMel",
+                    "attrs": {
+                        "feature_size": 128,
+                        "sampling_rate": 16000,
+                        "frame_length_ms": 20.0,
+                        "hop_length_ms": 10.0,
+                        "min_frequency": 0.0,
+                        "max_frequency": 8000.0,
+                        "preemphasis": 0.0,
+                        "preemphasis_htk_flavor": 1,
+                        "fft_overdrive": 0,
+                        "mel_floor": 0.001
+                    }
+                }
+            }
+        ]
+    }
+}

openvino-epcontext/chat_template.jinja

@@ -0,0 +1,360 @@
+{%- 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 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 -%}
+
+{%- 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|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if 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: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
+    {%- set prev_nt = namespace(role=None, found=false) -%}
+    {%- if loop.index0 > 0 -%}
+        {%- for j in range(loop.index0 - 1, -1, -1) -%}
+            {%- if not prev_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
+                    {%- set prev_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- set continue_same_model_turn = (role == 'model' and prev_nt.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') -%}
+    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- 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 -%}
+
+            {%- 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['tool_responses'] -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), 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') | default('unknown')) -%}
+                        {%- for tc in message['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') == 'image' -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') == '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['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' -%}
+                        {{- '<|image|>' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '<|video|>' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not has_content) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

openvino-epcontext/decoder/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e251388bd6e648c3b9e15f3c1516674acd4626f75e9acf4314a72c6319b105
+size 1511747694

openvino-epcontext/decoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432230cbec1f29029851ef5b0001cad8160ca82b9277b4e446259d55085dc176
+size 6092

openvino-epcontext/embedding/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5136d94197767d50592ee056f0cc8dcf7472f55ff3c7589bee7e2255c45268
+size 5510887040

openvino-epcontext/embedding/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1448f7545d9a89719a1665b5c2f83ee9b0514e2e995735511ae2d026f8822fd7
+size 792

openvino-epcontext/embedding/model.xml

@@ -0,0 +1,1338 @@
+<?xml version="1.0"?>
+<net name="onnx_Frontend_IR" version="11">
+	<layers>
+		<layer id="0" name="input_ids" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<rt_info>
+				<attribute name="old_api_map_element_type" version="0" value="i32" />
+			</rt_info>
+			<output>
+				<port id="0" precision="I64" names="input_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="image_features" type="Parameter" version="opset1">
+			<data shape="?,1536" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="image_features">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="audio_features" type="Parameter" version="opset1">
+			<data shape="?,1536" element_type="f16" />
+			<output>
+				<port id="0" precision="FP16" names="audio_features">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_2698" type="Const" version="opset1">
+			<data element_type="i64" shape="1, 1" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="embedding/Equal_node_19" type="Equal" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL" names="v_embedding.Equal_19">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="const_1d_1" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" names="const_1d_1">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="embedding/Unsqueeze_node_20" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL" names="v_embedding.Unsqueeze_20">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="v_embedding.Unsqueeze_30" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1536" offset="16" size="3072" />
+			<output>
+				<port id="0" precision="FP16" names="v_embedding.Unsqueeze_30">
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="embedding/Concat_node_31" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Concat_31">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="embedding/Cast_node_21" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="v_embedding.Cast_21">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="embedding/Constant_node_6" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="3088" size="8" />
+			<output>
+				<port id="0" precision="I64" names="v_embedding.Constant_6" />
+			</output>
+		</layer>
+		<layer id="11" name="embedding/CumSum_node_23" type="CumSum" version="opset3">
+			<data exclusive="false" reverse="false" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" names="v_embedding.CumSum_23">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="12" name="Constant_2699" type="Const" version="opset1">
+			<data element_type="i64" shape="1, 1" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="13" name="embedding/Sub_node_25" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="v_embedding.Sub_25">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="embedding/Clip_node_27" type="Clamp" version="opset1">
+			<data min="0" max="9.2233720368547758e+18" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="v_embedding.Clip_27">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="Constant_36" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="3096" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="16" name="embedding/Gather_node_32" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="FP16" names="v_embedding.Gather_32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Constant_2700" type="Const" version="opset1">
+			<data element_type="i64" shape="1, 1" offset="3104" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="embedding/Equal_node_3" type="Equal" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL" names="v_embedding.Equal_3">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="embedding/Unsqueeze_node_4" type="Unsqueeze" version="opset1">
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL" names="v_embedding.Unsqueeze_4">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="v_embedding.Unsqueeze_14" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1536" offset="16" size="3072" />
+			<output>
+				<port id="0" precision="FP16" names="v_embedding.Unsqueeze_14">
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="embedding/Concat_node_15" type="Concat" version="opset1">
+			<data axis="0" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Concat_15">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="embedding/Cast_node_5" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="v_embedding.Cast_5">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="embedding/CumSum_node_7" type="CumSum" version="opset3">
+			<data exclusive="false" reverse="false" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" names="v_embedding.CumSum_7">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="Constant_2701" type="Const" version="opset1">
+			<data element_type="i64" shape="1, 1" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="embedding/Sub_node_9" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I64" names="v_embedding.Sub_9">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="embedding/Clip_node_11" type="Clamp" version="opset1">
+			<data min="0" max="9.2233720368547758e+18" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="v_embedding.Clip_11">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_55" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="3096" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="28" name="embedding/Gather_node_16" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="FP16" names="v_embedding.Gather_16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="embedding.embed_tokens.weight" type="Const" version="opset1">
+			<data element_type="f16" shape="262144, 1536" offset="3112" size="805306368" />
+			<output>
+				<port id="0" precision="FP16" names="embedding.embed_tokens.weight">
+					<dim>262144</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Constant_59" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="3096" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="31" name="embedding/embed_tokens/Gather_node_0" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="FP16" names="v_embedding.embed_tokens.Gather_0">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="Constant_2702" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1, 1" offset="805309480" size="2" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="embedding/embed_tokens/Mul_node_1" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.embed_tokens.Mul_1">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="embedding/Where_node_17" type="Select" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="2" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="FP16" names="v_embedding.Where_17">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="inputs_embeds" type="Select" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="2" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="FP16" names="inputs_embeds">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="Reshape_8" type="Const" version="opset1">
+			<data element_type="i4" shape="48, 32, 8960" offset="805309482" size="6881280" />
+			<output>
+				<port id="0" precision="I4">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="Convert_13" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I4">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Unsqueeze_10" type="Const" version="opset1">
+			<data element_type="i4" shape="48, 1, 8960" offset="812190762" size="215040" />
+			<output>
+				<port id="0" precision="I4">
+					<dim>48</dim>
+					<dim>1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="39" name="Convert_14" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I4">
+					<dim>48</dim>
+					<dim>1</dim>
+					<dim>8960</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>48</dim>
+					<dim>1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="40" name="Subtract_15" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>48</dim>
+					<dim>1</dim>
+					<dim>8960</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="41" name="Unsqueeze_11" type="Const" version="opset1">
+			<data element_type="f16" shape="48, 1, 8960" offset="812405802" size="860160" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>48</dim>
+					<dim>1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="42" name="Multiply_16" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>48</dim>
+					<dim>1</dim>
+					<dim>8960</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="43" name="Constant_2724" type="Const" version="opset1">
+			<data element_type="i64" shape="2" offset="813265962" size="16" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>2</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="44" name="embedding/per_layer_model_projection/MatMul_node_35_Q4_DequantizeLinear" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>48</dim>
+					<dim>32</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>2</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="embedding/per_layer_model_projection/MatMul_node_35_Q4_DequantizeLinear/output_0">
+					<dim>1536</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="embedding/per_layer_model_projection/MatMul_node_35_Q4_MatMul" type="MatMul" version="opset1">
+			<data transpose_a="false" transpose_b="false" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1536</dim>
+					<dim>8960</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="embedding/per_layer_model_projection/MatMul_node_35_Q4_MatMul/output_0">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="Constant_2703" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1, 1" offset="813265978" size="2" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="embedding/Mul_node_36" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Mul_36">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="48" name="embedding/Constant_node_37" type="Const" version="opset1">
+			<data element_type="i64" shape="4" offset="813265980" size="32" />
+			<output>
+				<port id="0" precision="I64" names="v_embedding.Constant_37">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="49" name="embedding/Reshape_node_38" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Reshape_38">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="50" name="Convert_70" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="51" name="Constant_2704" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1, 1" offset="813266012" size="4" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="52" name="Power_77" type="Power" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="53" name="Range_74" type="Const" version="opset1">
+			<data element_type="i64" shape="1" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="54" name="ReduceMean_78" type="ReduceMean" version="opset1">
+			<data keep_dims="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="55" name="Constant_2705" type="Const" version="opset1">
+			<data element_type="f32" shape="1, 1, 1, 1" offset="813266016" size="4" />
+			<output>
+				<port id="0" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="56" name="Add_80" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="57" name="Sqrt_81" type="Sqrt" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="58" name="Multiply_84" type="Divide" version="opset1">
+			<data auto_broadcast="numpy" m_pythondiv="true" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="59" name="ConvertLike_85" type="ConvertLike" version="opset1">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="60" name="Constant_2706" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1, 1, 256" offset="813266020" size="512" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="61" name="embedding/per_layer_projection_norm/RMSNormalization_node_39" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>256</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.per_layer_projection_norm.RMSNormalization_39">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="62" name="embedding.embed_tokens_per_layer.weight" type="Const" version="opset1">
+			<data element_type="f16" shape="262144, 8960" offset="813266532" size="4697620480" />
+			<output>
+				<port id="0" precision="FP16" names="embedding.embed_tokens_per_layer.weight">
+					<dim>262144</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="63" name="embedding/Constant_node_10" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="3096" size="8" />
+			<output>
+				<port id="0" precision="I64" names="v_embedding.Constant_10" />
+			</output>
+		</layer>
+		<layer id="64" name="embedding/Where_node_43" type="Select" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I64" names="v_embedding.Where_43">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="65" name="Constant_2707" type="Const" version="opset1">
+			<data element_type="i64" shape="1, 1" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="66" name="embedding/Equal_node_45" type="Equal" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="BOOL" names="v_embedding.Equal_45">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="67" name="embedding/Where_node_46" type="Select" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I64" names="v_embedding.Where_46">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="68" name="Constant_44" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="3096" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="69" name="embedding/embed_tokens_per_layer/Gather_node_47" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>262144</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="FP16" names="v_embedding.embed_tokens_per_layer.Gather_47">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="70" name="Constant_2708" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1, 1" offset="5510887012" size="2" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="71" name="embedding/embed_tokens_per_layer/Mul_node_48" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.embed_tokens_per_layer.Mul_48">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="72" name="embedding/Reshape_node_50" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>4</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Reshape_50">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="73" name="embedding/Add_node_51" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Add_51">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="74" name="Constant_2709" type="Const" version="opset1">
+			<data element_type="f16" shape="1, 1, 1, 1" offset="5510887014" size="2" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="75" name="embedding/Mul_node_52" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="v_embedding.Mul_52">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="76" name="embedding/Constant_node_53" type="Const" version="opset1">
+			<data element_type="i64" shape="3" offset="5510887016" size="24" />
+			<output>
+				<port id="0" precision="I64" names="v_embedding.Constant_53">
+					<dim>3</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="77" name="per_layer_inputs" type="Reshape" version="opset1">
+			<data special_zero="true" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>35</dim>
+					<dim>256</dim>
+				</port>
+				<port id="1" precision="I64">
+					<dim>3</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16" names="per_layer_inputs">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="78" name="inputs_embeds/sink_port_0" type="Result" version="opset1" output_names="inputs_embeds">
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+		</layer>
+		<layer id="79" name="per_layer_inputs/sink_port_0" type="Result" version="opset1" output_names="per_layer_inputs">
+			<input>
+				<port id="0" precision="FP16">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>8960</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="31" to-port="1" />
+		<edge from-layer="0" from-port="0" to-layer="4" to-port="0" />
+		<edge from-layer="0" from-port="0" to-layer="64" to-port="2" />
+		<edge from-layer="0" from-port="0" to-layer="18" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="21" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="8" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="6" to-port="0" />
+		<edge from-layer="4" from-port="2" to-layer="9" to-port="0" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="5" from-port="0" to-layer="19" to-port="1" />
+		<edge from-layer="6" from-port="2" to-layer="35" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="2" to-layer="16" to-port="0" />
+		<edge from-layer="9" from-port="1" to-layer="11" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="23" to-port="1" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="13" to-port="0" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
+		<edge from-layer="13" from-port="2" to-layer="14" to-port="0" />
+		<edge from-layer="14" from-port="1" to-layer="16" to-port="1" />
+		<edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
+		<edge from-layer="16" from-port="3" to-layer="35" to-port="1" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="1" />
+		<edge from-layer="18" from-port="2" to-layer="64" to-port="0" />
+		<edge from-layer="18" from-port="2" to-layer="19" to-port="0" />
+		<edge from-layer="18" from-port="2" to-layer="22" to-port="0" />
+		<edge from-layer="19" from-port="2" to-layer="34" to-port="0" />
+		<edge from-layer="20" from-port="0" to-layer="21" to-port="1" />
+		<edge from-layer="21" from-port="2" to-layer="28" to-port="0" />
+		<edge from-layer="22" from-port="1" to-layer="23" to-port="0" />
+		<edge from-layer="23" from-port="2" to-layer="25" to-port="0" />
+		<edge from-layer="24" from-port="0" to-layer="25" to-port="1" />
+		<edge from-layer="25" from-port="2" to-layer="26" to-port="0" />
+		<edge from-layer="26" from-port="1" to-layer="28" to-port="1" />
+		<edge from-layer="27" from-port="0" to-layer="28" to-port="2" />
+		<edge from-layer="28" from-port="3" to-layer="34" to-port="1" />
+		<edge from-layer="29" from-port="0" to-layer="31" to-port="0" />
+		<edge from-layer="30" from-port="0" to-layer="31" to-port="2" />
+		<edge from-layer="31" from-port="3" to-layer="33" to-port="0" />
+		<edge from-layer="32" from-port="0" to-layer="33" to-port="1" />
+		<edge from-layer="33" from-port="2" to-layer="34" to-port="2" />
+		<edge from-layer="34" from-port="3" to-layer="35" to-port="2" />
+		<edge from-layer="35" from-port="3" to-layer="45" to-port="0" />
+		<edge from-layer="35" from-port="3" to-layer="78" to-port="0" />
+		<edge from-layer="36" from-port="0" to-layer="37" to-port="0" />
+		<edge from-layer="37" from-port="1" to-layer="40" to-port="0" />
+		<edge from-layer="38" from-port="0" to-layer="39" to-port="0" />
+		<edge from-layer="39" from-port="1" to-layer="40" to-port="1" />
+		<edge from-layer="40" from-port="2" to-layer="42" to-port="0" />
+		<edge from-layer="41" from-port="0" to-layer="42" to-port="1" />
+		<edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
+		<edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
+		<edge from-layer="44" from-port="2" to-layer="45" to-port="1" />
+		<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
+		<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
+		<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
+		<edge from-layer="48" from-port="0" to-layer="72" to-port="1" />
+		<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
+		<edge from-layer="49" from-port="2" to-layer="50" to-port="0" />
+		<edge from-layer="49" from-port="2" to-layer="59" to-port="1" />
+		<edge from-layer="50" from-port="1" to-layer="52" to-port="0" />
+		<edge from-layer="50" from-port="1" to-layer="58" to-port="0" />
+		<edge from-layer="51" from-port="0" to-layer="52" to-port="1" />
+		<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
+		<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
+		<edge from-layer="54" from-port="2" to-layer="56" to-port="0" />
+		<edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
+		<edge from-layer="56" from-port="2" to-layer="57" to-port="0" />
+		<edge from-layer="57" from-port="1" to-layer="58" to-port="1" />
+		<edge from-layer="58" from-port="2" to-layer="59" to-port="0" />
+		<edge from-layer="59" from-port="2" to-layer="61" to-port="0" />
+		<edge from-layer="60" from-port="0" to-layer="61" to-port="1" />
+		<edge from-layer="61" from-port="2" to-layer="73" to-port="0" />
+		<edge from-layer="62" from-port="0" to-layer="69" to-port="0" />
+		<edge from-layer="63" from-port="0" to-layer="64" to-port="1" />
+		<edge from-layer="63" from-port="0" to-layer="67" to-port="1" />
+		<edge from-layer="64" from-port="3" to-layer="66" to-port="0" />
+		<edge from-layer="64" from-port="3" to-layer="67" to-port="2" />
+		<edge from-layer="65" from-port="0" to-layer="66" to-port="1" />
+		<edge from-layer="66" from-port="2" to-layer="67" to-port="0" />
+		<edge from-layer="67" from-port="3" to-layer="69" to-port="1" />
+		<edge from-layer="68" from-port="0" to-layer="69" to-port="2" />
+		<edge from-layer="69" from-port="3" to-layer="71" to-port="0" />
+		<edge from-layer="70" from-port="0" to-layer="71" to-port="1" />
+		<edge from-layer="71" from-port="2" to-layer="72" to-port="0" />
+		<edge from-layer="72" from-port="2" to-layer="73" to-port="1" />
+		<edge from-layer="73" from-port="2" to-layer="75" to-port="0" />
+		<edge from-layer="74" from-port="0" to-layer="75" to-port="1" />
+		<edge from-layer="75" from-port="2" to-layer="77" to-port="0" />
+		<edge from-layer="76" from-port="0" to-layer="77" to-port="1" />
+		<edge from-layer="77" from-port="2" to-layer="79" to-port="0" />
+	</edges>
+	<rt_info>
+		<info name="OpenVINO Runtime" value="2026.3.0-1-a04834c6ca3" />
+		<Runtime_version value="2026.3.0-1-a04834c6ca3" />
+		<conversion_parameters>
+			<input_model value="DIR/model.onnx" />
+			<is_python_object value="False" />
+		</conversion_parameters>
+		<framework>
+			<olive_version value="0.11.0.dev0" />
+		</framework>
+	</rt_info>
+</net>

openvino-epcontext/genai_config.json

@@ -0,0 +1,125 @@
+{
+    "model": {
+        "type": "gemma4",
+        "vocab_size": 262144,
+        "context_length": 131072,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "OpenVINO": {
+                            "device_type": "NPU"
+                        }
+                    }
+                ]
+            },
+            "filename": "decoder/model.onnx",
+            "head_size": 256,
+            "hidden_size": 1536,
+            "inputs": {
+                "inputs_embeds": "inputs_embeds",
+                "attention_mask": "attention_mask",
+                "position_ids": "position_ids",
+                "per_layer_inputs": "per_layer_inputs",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 8,
+            "num_hidden_layers": 35,
+            "num_key_value_heads": 1
+        },
+        "bos_token_id": 2,
+        "eos_token_id": [
+            1,
+            106
+        ],
+        "pad_token_id": 0,
+        "vision": {
+            "filename": "vision_encoder/model.onnx",
+            "config_filename": "image_processor.json",
+            "inputs": {
+                "pixel_values": "pixel_values",
+                "pixel_position_ids": "pixel_position_ids"
+            },
+            "outputs": {
+                "image_features": "image_features"
+            },
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "OpenVINO": {
+                            "device_type": "NPU"
+                        }
+                    }
+                ]
+            },
+            "spatial_merge_size": 2
+        },
+        "embedding": {
+            "filename": "embedding/model.onnx",
+            "inputs": {
+                "input_ids": "input_ids",
+                "image_features": "image_features",
+                "audio_features": "audio_features"
+            },
+            "outputs": {
+                "inputs_embeds": "inputs_embeds",
+                "per_layer_inputs": "per_layer_inputs"
+            },
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "OpenVINO": {
+                            "device_type": "NPU"
+                        }
+                    }
+                ]
+            }
+        },
+        "speech": {
+            "filename": "audio_encoder/model.onnx",
+            "config_filename": "audio_feature_extraction.json",
+            "inputs": {
+                "audio_embeds": "input_features",
+                "attention_mask": "input_features_mask"
+            },
+            "outputs": {
+                "audio_features": "audio_features"
+            },
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "OpenVINO": {
+                            "device_type": "NPU"
+                        }
+                    }
+                ]
+            }
+        },
+        "image_token_id": 258880,
+        "audio_token_id": 258881,
+        "boa_token_id": 256000
+    },
+    "search": {
+        "do_sample": true,
+        "early_stopping": true,
+        "max_length": 131072,
+        "min_length": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": false,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 1,
+        "top_p": 1.0
+    }
+}

openvino-epcontext/image_processor.json

@@ -0,0 +1,27 @@
+{
+    "processor": {
+        "name": "gemma_4_image_processing",
+        "transforms": [
+            {
+                "operation": {
+                    "name": "decode_image",
+                    "type": "DecodeImage",
+                    "attrs": {
+                        "color_space": "RGB"
+                    }
+                }
+            },
+            {
+                "operation": {
+                    "name": "gemma4_image_transform",
+                    "type": "Gemma4ImageTransform",
+                    "attrs": {
+                        "patch_size": 16,
+                        "max_soft_tokens": 280,
+                        "pooling_kernel_size": 3
+                    }
+                }
+            }
+        ]
+    }
+}

openvino-epcontext/tokenizer.json

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

openvino-epcontext/tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "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|>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "type": "object",
+    "properties": {
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "content": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
+        "type": "array",
+        "items": {
+          "type": "object",
+          "properties": {
+            "type": {
+              "const": "function"
+            },
+            "function": {
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
+              "properties": {
+                "name": {
+                  "type": "string"
+                },
+                "arguments": {
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call",
+                  "additionalProperties": {}
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|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>",
+  "chat_template": "{%- macro format_parameters(properties, required, filter_keys=false) -%}\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 not filter_keys or 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['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 == 'ARRAY' -%}\n                {%- if value['items'] is mapping and value['items'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\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 value['nullable'] %}\n                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                nullable:true\n            {%- endif -%}\n            {%- if value['type'] | upper == 'OBJECT' -%}\n                {%- if value['properties'] is defined and value['properties'] is mapping -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    properties:{\n                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n                    }\n                {%- elif value is mapping -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    properties:{\n                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n                    }\n                {%- endif -%}\n                {%- if value['required'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    required:[\n                    {%- for item in value['required'] | default([]) -%}\n                        <|\"|>{{- item -}}<|\"|>\n                        {%- if not loop.last %},{% 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{%- macro format_tool_response_block(tool_name, response) -%}\n    {{- '<|tool_response>' -}}\n    {%- if response is mapping -%}\n        {{- 'response:' + tool_name + '{' -}}\n        {%- for key, value in response | dictsort -%}\n            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n            {%- if not loop.last %},{% endif -%}\n        {%- endfor -%}\n        {{- '}' -}}\n    {%- else -%}\n        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n    {%- endif -%}\n    {{- '<tool_response|>' -}}\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    {#- Inject Thinking token at the very top of the FIRST system turn -#}\n    {%- if enable_thinking is defined and enable_thinking -%}\n        {{- '<|think|>\\n' -}}\n        {%- set ns.prev_message_type = 'think' -%}\n    {%- endif -%}\n    {%- if messages[0]['role'] in ['system', 'developer'] -%}\n        {%- if messages[0]['content'] is string -%}\n            {{- messages[0]['content'] | trim -}}\n        {%- elif messages[0]['content'] is sequence -%}\n            {%- for item in messages[0]['content'] -%}\n                {{- item['text'] | trim + ' '-}}\n            {%- endfor -%}\n        {%- endif -%}\n        {%- set loop_messages = messages[1:] -%}\n    {%- endif -%}\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    {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n    {%- if loop_messages[i]['role'] == 'user' -%}\n        {%- set ns_turn.last_user_idx = i -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n    {%- if message['role'] != 'tool' -%}\n    {%- set ns.prev_message_type = None -%}\n    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n    {%- set prev_nt = namespace(role=None, found=false) -%}\n    {%- if loop.index0 > 0 -%}\n        {%- for j in range(loop.index0 - 1, -1, -1) -%}\n            {%- if not prev_nt.found -%}\n                {%- if loop_messages[j]['role'] != 'tool' -%}\n                    {%- set prev_nt.role = loop_messages[j]['role'] -%}\n                    {%- set prev_nt.found = true -%}\n                {%- endif -%}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- endif -%}\n    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n    {%- if not continue_same_model_turn -%}\n        {{- '<|turn>' + role + '\\n' }}\n    {%- endif -%}\n\n    {#- Render reasoning/reasoning_content as thinking channel -#}\n    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n        {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n    {%- endif -%}\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            {%- set ns_tr_out = namespace(flag=false) -%}\n            {%- if message.get('tool_responses') -%}\n                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n                {%- for tool_response in message['tool_responses'] -%}\n                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n                    {%- set ns_tr_out.flag = true -%}\n                    {%- set ns.prev_message_type = 'tool_response' -%}\n                {%- endfor -%}\n            {%- elif message.get('tool_calls') -%}\n                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n                {%- set ns_tool_scan = namespace(stopped=false) -%}\n                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n                    {%- if ns_tool_scan.stopped -%}\n                    {%- elif loop_messages[k]['role'] != 'tool' -%}\n                        {%- set ns_tool_scan.stopped = true -%}\n                    {%- else -%}\n                        {%- set follow = loop_messages[k] -%}\n                        {#- Resolve tool_call_id to function name -#}\n                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n                        {%- for tc in message['tool_calls'] -%}\n                            {%- if tc.get('id') == follow.get('tool_call_id') -%}\n                                {%- set ns_tname.name = tc['function']['name'] -%}\n                            {%- endif -%}\n                        {%- endfor -%}\n                        {#- Handle content as string or content-parts array -#}\n                        {%- set tool_body = follow.get('content') -%}\n                        {%- if tool_body is string -%}\n                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n                        {%- elif tool_body is sequence and tool_body is not string -%}\n                            {%- set ns_txt = namespace(s='') -%}\n                            {%- for part in tool_body -%}\n                                {%- if part.get('type') == 'text' -%}\n                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n                                {%- endif -%}\n                            {%- endfor -%}\n                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n                            {%- for part in tool_body -%}\n                                {%- if part.get('type') == 'image' -%}\n                                    {{- '<|image|>' -}}\n                                {%- elif part.get('type') == 'audio' -%}\n                                    {{- '<|audio|>' -}}\n                                {%- elif part.get('type') == 'video' -%}\n                                    {{- '<|video|>' -}}\n                                {%- endif -%}\n                            {%- endfor -%}\n                        {%- else -%}\n                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n                        {%- endif -%}\n                        {%- set ns_tr_out.flag = true -%}\n                        {%- set ns.prev_message_type = 'tool_response' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n\n            {%- set captured_content -%}\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                        {{- '<|image|>' -}}\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                        {{- '<|video|>' -}}\n                        {%- set ns.prev_message_type = 'video' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n            {%- endset -%}\n\n            {{- captured_content -}}\n            {%- set has_content = captured_content | trim | length > 0 -%}\n\n        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n            {{- '<|tool_response>' -}}\n        {%- elif not (ns_tr_out.flag and not has_content) -%}\n            {{- '<turn|>\\n' -}}\n        {%- endif -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n        {{- '<|turn>model\\n' -}}\n    {%- endif -%}\n{%- endif -%}"
+}

openvino-epcontext/vision_encoder/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2353615bf90c78d6aa6934b94afcd9009c8344181fb62b03d7aafd6afbca13f4
+size 121186980

openvino-epcontext/vision_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b227f8330ae1d7c29f19cd6453670bf7851475a3a6e79e1789dc221b1eb7538
+size 672