Upload quantized model gemma-4-26B-AutoRound-MXFP8

.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 +1,24 @@
+---
+base_model:
+- google/gemma-4-26B
+pipeline_tag: text-generation
+tags:
+- quantized
+- mxfp8
+- autoround
+- autoquant-agent
+---
+
+# gemma-4-26B-AutoRound-MXFP8
+
+## Model Details
+
+This is a **MXFP8** quantization of [google/gemma-4-26B](https://huggingface.co/google/gemma-4-26B), generated by [AutoRound](https://github.com/intel/auto-round). Please follow the license of the original model.
+
+## Quantization Details
+
+- **Scheme:** MXFP8
+- **Method:** AutoRound
+- **Base model:** [google/gemma-4-26B](https://huggingface.co/google/gemma-4-26B)
+
+_Produced with [autoquant-agent](https://github.com/) — agent-driven quantize + evaluate + self-heal._

chat_template.jinja

@@ -0,0 +1,390 @@
+{#
+  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' -}}
+        {%- if not enable_thinking -%}
+            {{- '<|channel>thought\n<channel|>' -}}
+        {%- endif -%}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,844 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": null,
+  "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,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": true,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": true,
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2816,
+    "hidden_size_per_layer_input": 0,
+    "initializer_range": 0.02,
+    "intermediate_size": 2112,
+    "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"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": 704,
+    "num_attention_heads": 16,
+    "num_experts": 128,
+    "num_global_key_value_heads": 2,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 8,
+    "num_kv_shared_layers": 0,
+    "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": 1024,
+    "tie_word_embeddings": true,
+    "top_k_experts": 8,
+    "use_bidirectional_attention": "vision",
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 72,
+    "head_dim": 72,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "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": true,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "num_bits": 8,
+          "type": "float",
+          "symmetric": true,
+          "group_size": 32,
+          "strategy": "group",
+          "block_structure": null,
+          "dynamic": false,
+          "actorder": null,
+          "scale_dtype": "torch.uint8",
+          "zp_dtype": null,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {}
+        },
+        "input_activations": {
+          "num_bits": 8,
+          "type": "float",
+          "symmetric": true,
+          "group_size": 32,
+          "strategy": "group",
+          "block_structure": null,
+          "dynamic": true,
+          "actorder": null,
+          "scale_dtype": "torch.uint8",
+          "zp_dtype": null,
+          "observer": null,
+          "observer_kwargs": {}
+        },
+        "output_activations": null,
+        "format": null
+      }
+    },
+    "quant_method": "compressed-tensors",
+    "kv_cache_scheme": null,
+    "format": "mxfp8-quantized",
+    "quantization_status": "compressed",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.embed_vision.embedding_projection",
+      "model.language_model.embed_tokens",
+      "model.language_model.layers.0.input_layernorm",
+      "model.language_model.layers.0.post_attention_layernorm",
+      "model.language_model.layers.0.post_feedforward_layernorm",
+      "model.language_model.layers.0.post_feedforward_layernorm_1",
+      "model.language_model.layers.0.post_feedforward_layernorm_2",
+      "model.language_model.layers.0.pre_feedforward_layernorm",
+      "model.language_model.layers.0.pre_feedforward_layernorm_2",
+      "model.language_model.layers.0.router.proj",
+      "model.language_model.layers.0.self_attn.k_norm",
+      "model.language_model.layers.0.self_attn.q_norm",
+      "model.language_model.layers.1.input_layernorm",
+      "model.language_model.layers.1.post_attention_layernorm",
+      "model.language_model.layers.1.post_feedforward_layernorm",
+      "model.language_model.layers.1.post_feedforward_layernorm_1",
+      "model.language_model.layers.1.post_feedforward_layernorm_2",
+      "model.language_model.layers.1.pre_feedforward_layernorm",
+      "model.language_model.layers.1.pre_feedforward_layernorm_2",
+      "model.language_model.layers.1.router.proj",
+      "model.language_model.layers.1.self_attn.k_norm",
+      "model.language_model.layers.1.self_attn.q_norm",
+      "model.language_model.layers.10.input_layernorm",
+      "model.language_model.layers.10.post_attention_layernorm",
+      "model.language_model.layers.10.post_feedforward_layernorm",
+      "model.language_model.layers.10.post_feedforward_layernorm_1",
+      "model.language_model.layers.10.post_feedforward_layernorm_2",
+      "model.language_model.layers.10.pre_feedforward_layernorm",
+      "model.language_model.layers.10.pre_feedforward_layernorm_2",
+      "model.language_model.layers.10.router.proj",
+      "model.language_model.layers.10.self_attn.k_norm",
+      "model.language_model.layers.10.self_attn.q_norm",
+      "model.language_model.layers.11.input_layernorm",
+      "model.language_model.layers.11.post_attention_layernorm",
+      "model.language_model.layers.11.post_feedforward_layernorm",
+      "model.language_model.layers.11.post_feedforward_layernorm_1",
+      "model.language_model.layers.11.post_feedforward_layernorm_2",
+      "model.language_model.layers.11.pre_feedforward_layernorm",
+      "model.language_model.layers.11.pre_feedforward_layernorm_2",
+      "model.language_model.layers.11.router.proj",
+      "model.language_model.layers.11.self_attn.k_norm",
+      "model.language_model.layers.11.self_attn.q_norm",
+      "model.language_model.layers.12.input_layernorm",
+      "model.language_model.layers.12.post_attention_layernorm",
+      "model.language_model.layers.12.post_feedforward_layernorm",
+      "model.language_model.layers.12.post_feedforward_layernorm_1",
+      "model.language_model.layers.12.post_feedforward_layernorm_2",
+      "model.language_model.layers.12.pre_feedforward_layernorm",
+      "model.language_model.layers.12.pre_feedforward_layernorm_2",
+      "model.language_model.layers.12.router.proj",
+      "model.language_model.layers.12.self_attn.k_norm",
+      "model.language_model.layers.12.self_attn.q_norm",
+      "model.language_model.layers.13.input_layernorm",
+      "model.language_model.layers.13.post_attention_layernorm",
+      "model.language_model.layers.13.post_feedforward_layernorm",
+      "model.language_model.layers.13.post_feedforward_layernorm_1",
+      "model.language_model.layers.13.post_feedforward_layernorm_2",
+      "model.language_model.layers.13.pre_feedforward_layernorm",
+      "model.language_model.layers.13.pre_feedforward_layernorm_2",
+      "model.language_model.layers.13.router.proj",
+      "model.language_model.layers.13.self_attn.k_norm",
+      "model.language_model.layers.13.self_attn.q_norm",
+      "model.language_model.layers.14.input_layernorm",
+      "model.language_model.layers.14.post_attention_layernorm",
+      "model.language_model.layers.14.post_feedforward_layernorm",
+      "model.language_model.layers.14.post_feedforward_layernorm_1",
+      "model.language_model.layers.14.post_feedforward_layernorm_2",
+      "model.language_model.layers.14.pre_feedforward_layernorm",
+      "model.language_model.layers.14.pre_feedforward_layernorm_2",
+      "model.language_model.layers.14.router.proj",
+      "model.language_model.layers.14.self_attn.k_norm",
+      "model.language_model.layers.14.self_attn.q_norm",
+      "model.language_model.layers.15.input_layernorm",
+      "model.language_model.layers.15.post_attention_layernorm",
+      "model.language_model.layers.15.post_feedforward_layernorm",
+      "model.language_model.layers.15.post_feedforward_layernorm_1",
+      "model.language_model.layers.15.post_feedforward_layernorm_2",
+      "model.language_model.layers.15.pre_feedforward_layernorm",
+      "model.language_model.layers.15.pre_feedforward_layernorm_2",
+      "model.language_model.layers.15.router.proj",
+      "model.language_model.layers.15.self_attn.k_norm",
+      "model.language_model.layers.15.self_attn.q_norm",
+      "model.language_model.layers.16.input_layernorm",
+      "model.language_model.layers.16.post_attention_layernorm",
+      "model.language_model.layers.16.post_feedforward_layernorm",
+      "model.language_model.layers.16.post_feedforward_layernorm_1",
+      "model.language_model.layers.16.post_feedforward_layernorm_2",
+      "model.language_model.layers.16.pre_feedforward_layernorm",
+      "model.language_model.layers.16.pre_feedforward_layernorm_2",
+      "model.language_model.layers.16.router.proj",
+      "model.language_model.layers.16.self_attn.k_norm",
+      "model.language_model.layers.16.self_attn.q_norm",
+      "model.language_model.layers.17.input_layernorm",
+      "model.language_model.layers.17.post_attention_layernorm",
+      "model.language_model.layers.17.post_feedforward_layernorm",
+      "model.language_model.layers.17.post_feedforward_layernorm_1",
+      "model.language_model.layers.17.post_feedforward_layernorm_2",
+      "model.language_model.layers.17.pre_feedforward_layernorm",
+      "model.language_model.layers.17.pre_feedforward_layernorm_2",
+      "model.language_model.layers.17.router.proj",
+      "model.language_model.layers.17.self_attn.k_norm",
+      "model.language_model.layers.17.self_attn.q_norm",
+      "model.language_model.layers.18.input_layernorm",
+      "model.language_model.layers.18.post_attention_layernorm",
+      "model.language_model.layers.18.post_feedforward_layernorm",
+      "model.language_model.layers.18.post_feedforward_layernorm_1",
+      "model.language_model.layers.18.post_feedforward_layernorm_2",
+      "model.language_model.layers.18.pre_feedforward_layernorm",
+      "model.language_model.layers.18.pre_feedforward_layernorm_2",
+      "model.language_model.layers.18.router.proj",
+      "model.language_model.layers.18.self_attn.k_norm",
+      "model.language_model.layers.18.self_attn.q_norm",
+      "model.language_model.layers.19.input_layernorm",
+      "model.language_model.layers.19.post_attention_layernorm",
+      "model.language_model.layers.19.post_feedforward_layernorm",
+      "model.language_model.layers.19.post_feedforward_layernorm_1",
+      "model.language_model.layers.19.post_feedforward_layernorm_2",
+      "model.language_model.layers.19.pre_feedforward_layernorm",
+      "model.language_model.layers.19.pre_feedforward_layernorm_2",
+      "model.language_model.layers.19.router.proj",
+      "model.language_model.layers.19.self_attn.k_norm",
+      "model.language_model.layers.19.self_attn.q_norm",
+      "model.language_model.layers.2.input_layernorm",
+      "model.language_model.layers.2.post_attention_layernorm",
+      "model.language_model.layers.2.post_feedforward_layernorm",
+      "model.language_model.layers.2.post_feedforward_layernorm_1",
+      "model.language_model.layers.2.post_feedforward_layernorm_2",
+      "model.language_model.layers.2.pre_feedforward_layernorm",
+      "model.language_model.layers.2.pre_feedforward_layernorm_2",
+      "model.language_model.layers.2.router.proj",
+      "model.language_model.layers.2.self_attn.k_norm",
+      "model.language_model.layers.2.self_attn.q_norm",
+      "model.language_model.layers.20.input_layernorm",
+      "model.language_model.layers.20.post_attention_layernorm",
+      "model.language_model.layers.20.post_feedforward_layernorm",
+      "model.language_model.layers.20.post_feedforward_layernorm_1",
+      "model.language_model.layers.20.post_feedforward_layernorm_2",
+      "model.language_model.layers.20.pre_feedforward_layernorm",
+      "model.language_model.layers.20.pre_feedforward_layernorm_2",
+      "model.language_model.layers.20.router.proj",
+      "model.language_model.layers.20.self_attn.k_norm",
+      "model.language_model.layers.20.self_attn.q_norm",
+      "model.language_model.layers.21.input_layernorm",
+      "model.language_model.layers.21.post_attention_layernorm",
+      "model.language_model.layers.21.post_feedforward_layernorm",
+      "model.language_model.layers.21.post_feedforward_layernorm_1",
+      "model.language_model.layers.21.post_feedforward_layernorm_2",
+      "model.language_model.layers.21.pre_feedforward_layernorm",
+      "model.language_model.layers.21.pre_feedforward_layernorm_2",
+      "model.language_model.layers.21.router.proj",
+      "model.language_model.layers.21.self_attn.k_norm",
+      "model.language_model.layers.21.self_attn.q_norm",
+      "model.language_model.layers.22.input_layernorm",
+      "model.language_model.layers.22.post_attention_layernorm",
+      "model.language_model.layers.22.post_feedforward_layernorm",
+      "model.language_model.layers.22.post_feedforward_layernorm_1",
+      "model.language_model.layers.22.post_feedforward_layernorm_2",
+      "model.language_model.layers.22.pre_feedforward_layernorm",
+      "model.language_model.layers.22.pre_feedforward_layernorm_2",
+      "model.language_model.layers.22.router.proj",
+      "model.language_model.layers.22.self_attn.k_norm",
+      "model.language_model.layers.22.self_attn.q_norm",
+      "model.language_model.layers.23.input_layernorm",
+      "model.language_model.layers.23.post_attention_layernorm",
+      "model.language_model.layers.23.post_feedforward_layernorm",
+      "model.language_model.layers.23.post_feedforward_layernorm_1",
+      "model.language_model.layers.23.post_feedforward_layernorm_2",
+      "model.language_model.layers.23.pre_feedforward_layernorm",
+      "model.language_model.layers.23.pre_feedforward_layernorm_2",
+      "model.language_model.layers.23.router.proj",
+      "model.language_model.layers.23.self_attn.k_norm",
+      "model.language_model.layers.23.self_attn.q_norm",
+      "model.language_model.layers.24.input_layernorm",
+      "model.language_model.layers.24.post_attention_layernorm",
+      "model.language_model.layers.24.post_feedforward_layernorm",
+      "model.language_model.layers.24.post_feedforward_layernorm_1",
+      "model.language_model.layers.24.post_feedforward_layernorm_2",
+      "model.language_model.layers.24.pre_feedforward_layernorm",
+      "model.language_model.layers.24.pre_feedforward_layernorm_2",
+      "model.language_model.layers.24.router.proj",
+      "model.language_model.layers.24.self_attn.k_norm",
+      "model.language_model.layers.24.self_attn.q_norm",
+      "model.language_model.layers.25.input_layernorm",
+      "model.language_model.layers.25.post_attention_layernorm",
+      "model.language_model.layers.25.post_feedforward_layernorm",
+      "model.language_model.layers.25.post_feedforward_layernorm_1",
+      "model.language_model.layers.25.post_feedforward_layernorm_2",
+      "model.language_model.layers.25.pre_feedforward_layernorm",
+      "model.language_model.layers.25.pre_feedforward_layernorm_2",
+      "model.language_model.layers.25.router.proj",
+      "model.language_model.layers.25.self_attn.k_norm",
+      "model.language_model.layers.25.self_attn.q_norm",
+      "model.language_model.layers.26.input_layernorm",
+      "model.language_model.layers.26.post_attention_layernorm",
+      "model.language_model.layers.26.post_feedforward_layernorm",
+      "model.language_model.layers.26.post_feedforward_layernorm_1",
+      "model.language_model.layers.26.post_feedforward_layernorm_2",
+      "model.language_model.layers.26.pre_feedforward_layernorm",
+      "model.language_model.layers.26.pre_feedforward_layernorm_2",
+      "model.language_model.layers.26.router.proj",
+      "model.language_model.layers.26.self_attn.k_norm",
+      "model.language_model.layers.26.self_attn.q_norm",
+      "model.language_model.layers.27.input_layernorm",
+      "model.language_model.layers.27.post_attention_layernorm",
+      "model.language_model.layers.27.post_feedforward_layernorm",
+      "model.language_model.layers.27.post_feedforward_layernorm_1",
+      "model.language_model.layers.27.post_feedforward_layernorm_2",
+      "model.language_model.layers.27.pre_feedforward_layernorm",
+      "model.language_model.layers.27.pre_feedforward_layernorm_2",
+      "model.language_model.layers.27.router.proj",
+      "model.language_model.layers.27.self_attn.k_norm",
+      "model.language_model.layers.27.self_attn.q_norm",
+      "model.language_model.layers.28.input_layernorm",
+      "model.language_model.layers.28.post_attention_layernorm",
+      "model.language_model.layers.28.post_feedforward_layernorm",
+      "model.language_model.layers.28.post_feedforward_layernorm_1",
+      "model.language_model.layers.28.post_feedforward_layernorm_2",
+      "model.language_model.layers.28.pre_feedforward_layernorm",
+      "model.language_model.layers.28.pre_feedforward_layernorm_2",
+      "model.language_model.layers.28.router.proj",
+      "model.language_model.layers.28.self_attn.k_norm",
+      "model.language_model.layers.28.self_attn.q_norm",
+      "model.language_model.layers.29.input_layernorm",
+      "model.language_model.layers.29.post_attention_layernorm",
+      "model.language_model.layers.29.post_feedforward_layernorm",
+      "model.language_model.layers.29.post_feedforward_layernorm_1",
+      "model.language_model.layers.29.post_feedforward_layernorm_2",
+      "model.language_model.layers.29.pre_feedforward_layernorm",
+      "model.language_model.layers.29.pre_feedforward_layernorm_2",
+      "model.language_model.layers.29.router.proj",
+      "model.language_model.layers.29.self_attn.k_norm",
+      "model.language_model.layers.29.self_attn.q_norm",
+      "model.language_model.layers.3.input_layernorm",
+      "model.language_model.layers.3.post_attention_layernorm",
+      "model.language_model.layers.3.post_feedforward_layernorm",
+      "model.language_model.layers.3.post_feedforward_layernorm_1",
+      "model.language_model.layers.3.post_feedforward_layernorm_2",
+      "model.language_model.layers.3.pre_feedforward_layernorm",
+      "model.language_model.layers.3.pre_feedforward_layernorm_2",
+      "model.language_model.layers.3.router.proj",
+      "model.language_model.layers.3.self_attn.k_norm",
+      "model.language_model.layers.3.self_attn.q_norm",
+      "model.language_model.layers.4.input_layernorm",
+      "model.language_model.layers.4.post_attention_layernorm",
+      "model.language_model.layers.4.post_feedforward_layernorm",
+      "model.language_model.layers.4.post_feedforward_layernorm_1",
+      "model.language_model.layers.4.post_feedforward_layernorm_2",
+      "model.language_model.layers.4.pre_feedforward_layernorm",
+      "model.language_model.layers.4.pre_feedforward_layernorm_2",
+      "model.language_model.layers.4.router.proj",
+      "model.language_model.layers.4.self_attn.k_norm",
+      "model.language_model.layers.4.self_attn.q_norm",
+      "model.language_model.layers.5.input_layernorm",
+      "model.language_model.layers.5.post_attention_layernorm",
+      "model.language_model.layers.5.post_feedforward_layernorm",
+      "model.language_model.layers.5.post_feedforward_layernorm_1",
+      "model.language_model.layers.5.post_feedforward_layernorm_2",
+      "model.language_model.layers.5.pre_feedforward_layernorm",
+      "model.language_model.layers.5.pre_feedforward_layernorm_2",
+      "model.language_model.layers.5.router.proj",
+      "model.language_model.layers.5.self_attn.k_norm",
+      "model.language_model.layers.5.self_attn.q_norm",
+      "model.language_model.layers.6.input_layernorm",
+      "model.language_model.layers.6.post_attention_layernorm",
+      "model.language_model.layers.6.post_feedforward_layernorm",
+      "model.language_model.layers.6.post_feedforward_layernorm_1",
+      "model.language_model.layers.6.post_feedforward_layernorm_2",
+      "model.language_model.layers.6.pre_feedforward_layernorm",
+      "model.language_model.layers.6.pre_feedforward_layernorm_2",
+      "model.language_model.layers.6.router.proj",
+      "model.language_model.layers.6.self_attn.k_norm",
+      "model.language_model.layers.6.self_attn.q_norm",
+      "model.language_model.layers.7.input_layernorm",
+      "model.language_model.layers.7.post_attention_layernorm",
+      "model.language_model.layers.7.post_feedforward_layernorm",
+      "model.language_model.layers.7.post_feedforward_layernorm_1",
+      "model.language_model.layers.7.post_feedforward_layernorm_2",
+      "model.language_model.layers.7.pre_feedforward_layernorm",
+      "model.language_model.layers.7.pre_feedforward_layernorm_2",
+      "model.language_model.layers.7.router.proj",
+      "model.language_model.layers.7.self_attn.k_norm",
+      "model.language_model.layers.7.self_attn.q_norm",
+      "model.language_model.layers.8.input_layernorm",
+      "model.language_model.layers.8.post_attention_layernorm",
+      "model.language_model.layers.8.post_feedforward_layernorm",
+      "model.language_model.layers.8.post_feedforward_layernorm_1",
+      "model.language_model.layers.8.post_feedforward_layernorm_2",
+      "model.language_model.layers.8.pre_feedforward_layernorm",
+      "model.language_model.layers.8.pre_feedforward_layernorm_2",
+      "model.language_model.layers.8.router.proj",
+      "model.language_model.layers.8.self_attn.k_norm",
+      "model.language_model.layers.8.self_attn.q_norm",
+      "model.language_model.layers.9.input_layernorm",
+      "model.language_model.layers.9.post_attention_layernorm",
+      "model.language_model.layers.9.post_feedforward_layernorm",
+      "model.language_model.layers.9.post_feedforward_layernorm_1",
+      "model.language_model.layers.9.post_feedforward_layernorm_2",
+      "model.language_model.layers.9.pre_feedforward_layernorm",
+      "model.language_model.layers.9.pre_feedforward_layernorm_2",
+      "model.language_model.layers.9.router.proj",
+      "model.language_model.layers.9.self_attn.k_norm",
+      "model.language_model.layers.9.self_attn.q_norm",
+      "model.language_model.norm",
+      "model.vision_tower.encoder.layers.0.input_layernorm",
+      "model.vision_tower.encoder.layers.0.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.0.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.0.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.0.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.0.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.0.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.1.input_layernorm",
+      "model.vision_tower.encoder.layers.1.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.1.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.1.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.1.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.1.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.10.input_layernorm",
+      "model.vision_tower.encoder.layers.10.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.10.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.10.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.10.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.10.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.11.input_layernorm",
+      "model.vision_tower.encoder.layers.11.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.11.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.11.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.11.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.11.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.12.input_layernorm",
+      "model.vision_tower.encoder.layers.12.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.12.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.12.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.12.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.12.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.13.input_layernorm",
+      "model.vision_tower.encoder.layers.13.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.13.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.13.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.13.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.13.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.14.input_layernorm",
+      "model.vision_tower.encoder.layers.14.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.14.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.14.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.14.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.14.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.15.input_layernorm",
+      "model.vision_tower.encoder.layers.15.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.15.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.15.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.15.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.15.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.16.input_layernorm",
+      "model.vision_tower.encoder.layers.16.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.16.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.16.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.16.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.16.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.17.input_layernorm",
+      "model.vision_tower.encoder.layers.17.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.17.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.17.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.17.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.17.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.18.input_layernorm",
+      "model.vision_tower.encoder.layers.18.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.18.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.18.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.18.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.18.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.19.input_layernorm",
+      "model.vision_tower.encoder.layers.19.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.19.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.19.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.19.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.19.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.2.input_layernorm",
+      "model.vision_tower.encoder.layers.2.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.2.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.2.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.2.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.2.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.20.input_layernorm",
+      "model.vision_tower.encoder.layers.20.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.20.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.20.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.20.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.20.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.21.input_layernorm",
+      "model.vision_tower.encoder.layers.21.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.21.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.21.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.21.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.21.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.22.input_layernorm",
+      "model.vision_tower.encoder.layers.22.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.22.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.22.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.22.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.22.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.23.input_layernorm",
+      "model.vision_tower.encoder.layers.23.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.23.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.23.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.23.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.23.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.24.input_layernorm",
+      "model.vision_tower.encoder.layers.24.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.24.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.24.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.24.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.24.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.25.input_layernorm",
+      "model.vision_tower.encoder.layers.25.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.25.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.25.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.25.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.25.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.26.input_layernorm",
+      "model.vision_tower.encoder.layers.26.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.26.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.26.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.26.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.26.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.3.input_layernorm",
+      "model.vision_tower.encoder.layers.3.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.3.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.3.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.3.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.3.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.4.input_layernorm",
+      "model.vision_tower.encoder.layers.4.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.4.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.4.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.4.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.4.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.5.input_layernorm",
+      "model.vision_tower.encoder.layers.5.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.5.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.5.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.5.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.5.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.6.input_layernorm",
+      "model.vision_tower.encoder.layers.6.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.6.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.6.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.6.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.6.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.7.input_layernorm",
+      "model.vision_tower.encoder.layers.7.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.7.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.7.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.7.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.7.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.8.input_layernorm",
+      "model.vision_tower.encoder.layers.8.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.8.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.8.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.8.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.8.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear",
+      "model.vision_tower.encoder.layers.9.input_layernorm",
+      "model.vision_tower.encoder.layers.9.mlp.down_proj.linear",
+      "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear",
+      "model.vision_tower.encoder.layers.9.mlp.up_proj.linear",
+      "model.vision_tower.encoder.layers.9.post_attention_layernorm",
+      "model.vision_tower.encoder.layers.9.post_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm",
+      "model.vision_tower.encoder.layers.9.self_attn.k_norm",
+      "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.q_norm",
+      "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear",
+      "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear",
+      "model.vision_tower.patch_embedder.input_proj"
+    ],
+    "provider": "auto-round"
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8cb1f99cce49205cc290307948a5e3833bf16a54611a4401f079af61cda799
+size 27015946084

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff35824e9e3cbe92e794c15d332015df4fc3228ffca704b016b9dc1cffd3dd7d
+size 880970336

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"
+  }
+}

quantization_config.json

@@ -0,0 +1,702 @@
+{
+  "config_groups": {
+    "group_0": {
+      "targets": [
+        "Linear"
+      ],
+      "weights": {
+        "num_bits": 8,
+        "type": "float",
+        "symmetric": true,
+        "group_size": 32,
+        "strategy": "group",
+        "block_structure": null,
+        "dynamic": false,
+        "actorder": null,
+        "scale_dtype": "torch.uint8",
+        "zp_dtype": null,
+        "observer": "memoryless_minmax",
+        "observer_kwargs": {}
+      },
+      "input_activations": {
+        "num_bits": 8,
+        "type": "float",
+        "symmetric": true,
+        "group_size": 32,
+        "strategy": "group",
+        "block_structure": null,
+        "dynamic": true,
+        "actorder": null,
+        "scale_dtype": "torch.uint8",
+        "zp_dtype": null,
+        "observer": null,
+        "observer_kwargs": {}
+      },
+      "output_activations": null,
+      "format": null
+    }
+  },
+  "quant_method": "compressed-tensors",
+  "kv_cache_scheme": null,
+  "format": "mxfp8-quantized",
+  "quantization_status": "compressed",
+  "global_compression_ratio": null,
+  "ignore": [
+    "model.embed_vision.embedding_projection",
+    "model.language_model.embed_tokens",
+    "model.language_model.layers.0.input_layernorm",
+    "model.language_model.layers.0.post_attention_layernorm",
+    "model.language_model.layers.0.post_feedforward_layernorm",
+    "model.language_model.layers.0.post_feedforward_layernorm_1",
+    "model.language_model.layers.0.post_feedforward_layernorm_2",
+    "model.language_model.layers.0.pre_feedforward_layernorm",
+    "model.language_model.layers.0.pre_feedforward_layernorm_2",
+    "model.language_model.layers.0.router.proj",
+    "model.language_model.layers.0.self_attn.k_norm",
+    "model.language_model.layers.0.self_attn.q_norm",
+    "model.language_model.layers.1.input_layernorm",
+    "model.language_model.layers.1.post_attention_layernorm",
+    "model.language_model.layers.1.post_feedforward_layernorm",
+    "model.language_model.layers.1.post_feedforward_layernorm_1",
+    "model.language_model.layers.1.post_feedforward_layernorm_2",
+    "model.language_model.layers.1.pre_feedforward_layernorm",
+    "model.language_model.layers.1.pre_feedforward_layernorm_2",
+    "model.language_model.layers.1.router.proj",
+    "model.language_model.layers.1.self_attn.k_norm",
+    "model.language_model.layers.1.self_attn.q_norm",
+    "model.language_model.layers.10.input_layernorm",
+    "model.language_model.layers.10.post_attention_layernorm",
+    "model.language_model.layers.10.post_feedforward_layernorm",
+    "model.language_model.layers.10.post_feedforward_layernorm_1",
+    "model.language_model.layers.10.post_feedforward_layernorm_2",
+    "model.language_model.layers.10.pre_feedforward_layernorm",
+    "model.language_model.layers.10.pre_feedforward_layernorm_2",
+    "model.language_model.layers.10.router.proj",
+    "model.language_model.layers.10.self_attn.k_norm",
+    "model.language_model.layers.10.self_attn.q_norm",
+    "model.language_model.layers.11.input_layernorm",
+    "model.language_model.layers.11.post_attention_layernorm",
+    "model.language_model.layers.11.post_feedforward_layernorm",
+    "model.language_model.layers.11.post_feedforward_layernorm_1",
+    "model.language_model.layers.11.post_feedforward_layernorm_2",
+    "model.language_model.layers.11.pre_feedforward_layernorm",
+    "model.language_model.layers.11.pre_feedforward_layernorm_2",
+    "model.language_model.layers.11.router.proj",
+    "model.language_model.layers.11.self_attn.k_norm",
+    "model.language_model.layers.11.self_attn.q_norm",
+    "model.language_model.layers.12.input_layernorm",
+    "model.language_model.layers.12.post_attention_layernorm",
+    "model.language_model.layers.12.post_feedforward_layernorm",
+    "model.language_model.layers.12.post_feedforward_layernorm_1",
+    "model.language_model.layers.12.post_feedforward_layernorm_2",
+    "model.language_model.layers.12.pre_feedforward_layernorm",
+    "model.language_model.layers.12.pre_feedforward_layernorm_2",
+    "model.language_model.layers.12.router.proj",
+    "model.language_model.layers.12.self_attn.k_norm",
+    "model.language_model.layers.12.self_attn.q_norm",
+    "model.language_model.layers.13.input_layernorm",
+    "model.language_model.layers.13.post_attention_layernorm",
+    "model.language_model.layers.13.post_feedforward_layernorm",
+    "model.language_model.layers.13.post_feedforward_layernorm_1",
+    "model.language_model.layers.13.post_feedforward_layernorm_2",
+    "model.language_model.layers.13.pre_feedforward_layernorm",
+    "model.language_model.layers.13.pre_feedforward_layernorm_2",
+    "model.language_model.layers.13.router.proj",
+    "model.language_model.layers.13.self_attn.k_norm",
+    "model.language_model.layers.13.self_attn.q_norm",
+    "model.language_model.layers.14.input_layernorm",
+    "model.language_model.layers.14.post_attention_layernorm",
+    "model.language_model.layers.14.post_feedforward_layernorm",
+    "model.language_model.layers.14.post_feedforward_layernorm_1",
+    "model.language_model.layers.14.post_feedforward_layernorm_2",
+    "model.language_model.layers.14.pre_feedforward_layernorm",
+    "model.language_model.layers.14.pre_feedforward_layernorm_2",
+    "model.language_model.layers.14.router.proj",
+    "model.language_model.layers.14.self_attn.k_norm",
+    "model.language_model.layers.14.self_attn.q_norm",
+    "model.language_model.layers.15.input_layernorm",
+    "model.language_model.layers.15.post_attention_layernorm",
+    "model.language_model.layers.15.post_feedforward_layernorm",
+    "model.language_model.layers.15.post_feedforward_layernorm_1",
+    "model.language_model.layers.15.post_feedforward_layernorm_2",
+    "model.language_model.layers.15.pre_feedforward_layernorm",
+    "model.language_model.layers.15.pre_feedforward_layernorm_2",
+    "model.language_model.layers.15.router.proj",
+    "model.language_model.layers.15.self_attn.k_norm",
+    "model.language_model.layers.15.self_attn.q_norm",
+    "model.language_model.layers.16.input_layernorm",
+    "model.language_model.layers.16.post_attention_layernorm",
+    "model.language_model.layers.16.post_feedforward_layernorm",
+    "model.language_model.layers.16.post_feedforward_layernorm_1",
+    "model.language_model.layers.16.post_feedforward_layernorm_2",
+    "model.language_model.layers.16.pre_feedforward_layernorm",
+    "model.language_model.layers.16.pre_feedforward_layernorm_2",
+    "model.language_model.layers.16.router.proj",
+    "model.language_model.layers.16.self_attn.k_norm",
+    "model.language_model.layers.16.self_attn.q_norm",
+    "model.language_model.layers.17.input_layernorm",
+    "model.language_model.layers.17.post_attention_layernorm",
+    "model.language_model.layers.17.post_feedforward_layernorm",
+    "model.language_model.layers.17.post_feedforward_layernorm_1",
+    "model.language_model.layers.17.post_feedforward_layernorm_2",
+    "model.language_model.layers.17.pre_feedforward_layernorm",
+    "model.language_model.layers.17.pre_feedforward_layernorm_2",
+    "model.language_model.layers.17.router.proj",
+    "model.language_model.layers.17.self_attn.k_norm",
+    "model.language_model.layers.17.self_attn.q_norm",
+    "model.language_model.layers.18.input_layernorm",
+    "model.language_model.layers.18.post_attention_layernorm",
+    "model.language_model.layers.18.post_feedforward_layernorm",
+    "model.language_model.layers.18.post_feedforward_layernorm_1",
+    "model.language_model.layers.18.post_feedforward_layernorm_2",
+    "model.language_model.layers.18.pre_feedforward_layernorm",
+    "model.language_model.layers.18.pre_feedforward_layernorm_2",
+    "model.language_model.layers.18.router.proj",
+    "model.language_model.layers.18.self_attn.k_norm",
+    "model.language_model.layers.18.self_attn.q_norm",
+    "model.language_model.layers.19.input_layernorm",
+    "model.language_model.layers.19.post_attention_layernorm",
+    "model.language_model.layers.19.post_feedforward_layernorm",
+    "model.language_model.layers.19.post_feedforward_layernorm_1",
+    "model.language_model.layers.19.post_feedforward_layernorm_2",
+    "model.language_model.layers.19.pre_feedforward_layernorm",
+    "model.language_model.layers.19.pre_feedforward_layernorm_2",
+    "model.language_model.layers.19.router.proj",
+    "model.language_model.layers.19.self_attn.k_norm",
+    "model.language_model.layers.19.self_attn.q_norm",
+    "model.language_model.layers.2.input_layernorm",
+    "model.language_model.layers.2.post_attention_layernorm",
+    "model.language_model.layers.2.post_feedforward_layernorm",
+    "model.language_model.layers.2.post_feedforward_layernorm_1",
+    "model.language_model.layers.2.post_feedforward_layernorm_2",
+    "model.language_model.layers.2.pre_feedforward_layernorm",
+    "model.language_model.layers.2.pre_feedforward_layernorm_2",
+    "model.language_model.layers.2.router.proj",
+    "model.language_model.layers.2.self_attn.k_norm",
+    "model.language_model.layers.2.self_attn.q_norm",
+    "model.language_model.layers.20.input_layernorm",
+    "model.language_model.layers.20.post_attention_layernorm",
+    "model.language_model.layers.20.post_feedforward_layernorm",
+    "model.language_model.layers.20.post_feedforward_layernorm_1",
+    "model.language_model.layers.20.post_feedforward_layernorm_2",
+    "model.language_model.layers.20.pre_feedforward_layernorm",
+    "model.language_model.layers.20.pre_feedforward_layernorm_2",
+    "model.language_model.layers.20.router.proj",
+    "model.language_model.layers.20.self_attn.k_norm",
+    "model.language_model.layers.20.self_attn.q_norm",
+    "model.language_model.layers.21.input_layernorm",
+    "model.language_model.layers.21.post_attention_layernorm",
+    "model.language_model.layers.21.post_feedforward_layernorm",
+    "model.language_model.layers.21.post_feedforward_layernorm_1",
+    "model.language_model.layers.21.post_feedforward_layernorm_2",
+    "model.language_model.layers.21.pre_feedforward_layernorm",
+    "model.language_model.layers.21.pre_feedforward_layernorm_2",
+    "model.language_model.layers.21.router.proj",
+    "model.language_model.layers.21.self_attn.k_norm",
+    "model.language_model.layers.21.self_attn.q_norm",
+    "model.language_model.layers.22.input_layernorm",
+    "model.language_model.layers.22.post_attention_layernorm",
+    "model.language_model.layers.22.post_feedforward_layernorm",
+    "model.language_model.layers.22.post_feedforward_layernorm_1",
+    "model.language_model.layers.22.post_feedforward_layernorm_2",
+    "model.language_model.layers.22.pre_feedforward_layernorm",
+    "model.language_model.layers.22.pre_feedforward_layernorm_2",
+    "model.language_model.layers.22.router.proj",
+    "model.language_model.layers.22.self_attn.k_norm",
+    "model.language_model.layers.22.self_attn.q_norm",
+    "model.language_model.layers.23.input_layernorm",
+    "model.language_model.layers.23.post_attention_layernorm",
+    "model.language_model.layers.23.post_feedforward_layernorm",
+    "model.language_model.layers.23.post_feedforward_layernorm_1",
+    "model.language_model.layers.23.post_feedforward_layernorm_2",
+    "model.language_model.layers.23.pre_feedforward_layernorm",
+    "model.language_model.layers.23.pre_feedforward_layernorm_2",
+    "model.language_model.layers.23.router.proj",
+    "model.language_model.layers.23.self_attn.k_norm",
+    "model.language_model.layers.23.self_attn.q_norm",
+    "model.language_model.layers.24.input_layernorm",
+    "model.language_model.layers.24.post_attention_layernorm",
+    "model.language_model.layers.24.post_feedforward_layernorm",
+    "model.language_model.layers.24.post_feedforward_layernorm_1",
+    "model.language_model.layers.24.post_feedforward_layernorm_2",
+    "model.language_model.layers.24.pre_feedforward_layernorm",
+    "model.language_model.layers.24.pre_feedforward_layernorm_2",
+    "model.language_model.layers.24.router.proj",
+    "model.language_model.layers.24.self_attn.k_norm",
+    "model.language_model.layers.24.self_attn.q_norm",
+    "model.language_model.layers.25.input_layernorm",
+    "model.language_model.layers.25.post_attention_layernorm",
+    "model.language_model.layers.25.post_feedforward_layernorm",
+    "model.language_model.layers.25.post_feedforward_layernorm_1",
+    "model.language_model.layers.25.post_feedforward_layernorm_2",
+    "model.language_model.layers.25.pre_feedforward_layernorm",
+    "model.language_model.layers.25.pre_feedforward_layernorm_2",
+    "model.language_model.layers.25.router.proj",
+    "model.language_model.layers.25.self_attn.k_norm",
+    "model.language_model.layers.25.self_attn.q_norm",
+    "model.language_model.layers.26.input_layernorm",
+    "model.language_model.layers.26.post_attention_layernorm",
+    "model.language_model.layers.26.post_feedforward_layernorm",
+    "model.language_model.layers.26.post_feedforward_layernorm_1",
+    "model.language_model.layers.26.post_feedforward_layernorm_2",
+    "model.language_model.layers.26.pre_feedforward_layernorm",
+    "model.language_model.layers.26.pre_feedforward_layernorm_2",
+    "model.language_model.layers.26.router.proj",
+    "model.language_model.layers.26.self_attn.k_norm",
+    "model.language_model.layers.26.self_attn.q_norm",
+    "model.language_model.layers.27.input_layernorm",
+    "model.language_model.layers.27.post_attention_layernorm",
+    "model.language_model.layers.27.post_feedforward_layernorm",
+    "model.language_model.layers.27.post_feedforward_layernorm_1",
+    "model.language_model.layers.27.post_feedforward_layernorm_2",
+    "model.language_model.layers.27.pre_feedforward_layernorm",
+    "model.language_model.layers.27.pre_feedforward_layernorm_2",
+    "model.language_model.layers.27.router.proj",
+    "model.language_model.layers.27.self_attn.k_norm",
+    "model.language_model.layers.27.self_attn.q_norm",
+    "model.language_model.layers.28.input_layernorm",
+    "model.language_model.layers.28.post_attention_layernorm",
+    "model.language_model.layers.28.post_feedforward_layernorm",
+    "model.language_model.layers.28.post_feedforward_layernorm_1",
+    "model.language_model.layers.28.post_feedforward_layernorm_2",
+    "model.language_model.layers.28.pre_feedforward_layernorm",
+    "model.language_model.layers.28.pre_feedforward_layernorm_2",
+    "model.language_model.layers.28.router.proj",
+    "model.language_model.layers.28.self_attn.k_norm",
+    "model.language_model.layers.28.self_attn.q_norm",
+    "model.language_model.layers.29.input_layernorm",
+    "model.language_model.layers.29.post_attention_layernorm",
+    "model.language_model.layers.29.post_feedforward_layernorm",
+    "model.language_model.layers.29.post_feedforward_layernorm_1",
+    "model.language_model.layers.29.post_feedforward_layernorm_2",
+    "model.language_model.layers.29.pre_feedforward_layernorm",
+    "model.language_model.layers.29.pre_feedforward_layernorm_2",
+    "model.language_model.layers.29.router.proj",
+    "model.language_model.layers.29.self_attn.k_norm",
+    "model.language_model.layers.29.self_attn.q_norm",
+    "model.language_model.layers.3.input_layernorm",
+    "model.language_model.layers.3.post_attention_layernorm",
+    "model.language_model.layers.3.post_feedforward_layernorm",
+    "model.language_model.layers.3.post_feedforward_layernorm_1",
+    "model.language_model.layers.3.post_feedforward_layernorm_2",
+    "model.language_model.layers.3.pre_feedforward_layernorm",
+    "model.language_model.layers.3.pre_feedforward_layernorm_2",
+    "model.language_model.layers.3.router.proj",
+    "model.language_model.layers.3.self_attn.k_norm",
+    "model.language_model.layers.3.self_attn.q_norm",
+    "model.language_model.layers.4.input_layernorm",
+    "model.language_model.layers.4.post_attention_layernorm",
+    "model.language_model.layers.4.post_feedforward_layernorm",
+    "model.language_model.layers.4.post_feedforward_layernorm_1",
+    "model.language_model.layers.4.post_feedforward_layernorm_2",
+    "model.language_model.layers.4.pre_feedforward_layernorm",
+    "model.language_model.layers.4.pre_feedforward_layernorm_2",
+    "model.language_model.layers.4.router.proj",
+    "model.language_model.layers.4.self_attn.k_norm",
+    "model.language_model.layers.4.self_attn.q_norm",
+    "model.language_model.layers.5.input_layernorm",
+    "model.language_model.layers.5.post_attention_layernorm",
+    "model.language_model.layers.5.post_feedforward_layernorm",
+    "model.language_model.layers.5.post_feedforward_layernorm_1",
+    "model.language_model.layers.5.post_feedforward_layernorm_2",
+    "model.language_model.layers.5.pre_feedforward_layernorm",
+    "model.language_model.layers.5.pre_feedforward_layernorm_2",
+    "model.language_model.layers.5.router.proj",
+    "model.language_model.layers.5.self_attn.k_norm",
+    "model.language_model.layers.5.self_attn.q_norm",
+    "model.language_model.layers.6.input_layernorm",
+    "model.language_model.layers.6.post_attention_layernorm",
+    "model.language_model.layers.6.post_feedforward_layernorm",
+    "model.language_model.layers.6.post_feedforward_layernorm_1",
+    "model.language_model.layers.6.post_feedforward_layernorm_2",
+    "model.language_model.layers.6.pre_feedforward_layernorm",
+    "model.language_model.layers.6.pre_feedforward_layernorm_2",
+    "model.language_model.layers.6.router.proj",
+    "model.language_model.layers.6.self_attn.k_norm",
+    "model.language_model.layers.6.self_attn.q_norm",
+    "model.language_model.layers.7.input_layernorm",
+    "model.language_model.layers.7.post_attention_layernorm",
+    "model.language_model.layers.7.post_feedforward_layernorm",
+    "model.language_model.layers.7.post_feedforward_layernorm_1",
+    "model.language_model.layers.7.post_feedforward_layernorm_2",
+    "model.language_model.layers.7.pre_feedforward_layernorm",
+    "model.language_model.layers.7.pre_feedforward_layernorm_2",
+    "model.language_model.layers.7.router.proj",
+    "model.language_model.layers.7.self_attn.k_norm",
+    "model.language_model.layers.7.self_attn.q_norm",
+    "model.language_model.layers.8.input_layernorm",
+    "model.language_model.layers.8.post_attention_layernorm",
+    "model.language_model.layers.8.post_feedforward_layernorm",
+    "model.language_model.layers.8.post_feedforward_layernorm_1",
+    "model.language_model.layers.8.post_feedforward_layernorm_2",
+    "model.language_model.layers.8.pre_feedforward_layernorm",
+    "model.language_model.layers.8.pre_feedforward_layernorm_2",
+    "model.language_model.layers.8.router.proj",
+    "model.language_model.layers.8.self_attn.k_norm",
+    "model.language_model.layers.8.self_attn.q_norm",
+    "model.language_model.layers.9.input_layernorm",
+    "model.language_model.layers.9.post_attention_layernorm",
+    "model.language_model.layers.9.post_feedforward_layernorm",
+    "model.language_model.layers.9.post_feedforward_layernorm_1",
+    "model.language_model.layers.9.post_feedforward_layernorm_2",
+    "model.language_model.layers.9.pre_feedforward_layernorm",
+    "model.language_model.layers.9.pre_feedforward_layernorm_2",
+    "model.language_model.layers.9.router.proj",
+    "model.language_model.layers.9.self_attn.k_norm",
+    "model.language_model.layers.9.self_attn.q_norm",
+    "model.language_model.norm",
+    "model.vision_tower.encoder.layers.0.input_layernorm",
+    "model.vision_tower.encoder.layers.0.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.0.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.0.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.0.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.0.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.0.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.1.input_layernorm",
+    "model.vision_tower.encoder.layers.1.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.1.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.1.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.1.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.1.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.1.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.10.input_layernorm",
+    "model.vision_tower.encoder.layers.10.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.10.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.10.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.10.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.10.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.10.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.11.input_layernorm",
+    "model.vision_tower.encoder.layers.11.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.11.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.11.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.11.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.11.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.11.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.12.input_layernorm",
+    "model.vision_tower.encoder.layers.12.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.12.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.12.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.12.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.12.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.12.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.13.input_layernorm",
+    "model.vision_tower.encoder.layers.13.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.13.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.13.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.13.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.13.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.13.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.14.input_layernorm",
+    "model.vision_tower.encoder.layers.14.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.14.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.14.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.14.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.14.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.14.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.15.input_layernorm",
+    "model.vision_tower.encoder.layers.15.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.15.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.15.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.15.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.15.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.15.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.16.input_layernorm",
+    "model.vision_tower.encoder.layers.16.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.16.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.16.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.16.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.16.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.16.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.17.input_layernorm",
+    "model.vision_tower.encoder.layers.17.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.17.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.17.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.17.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.17.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.17.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.18.input_layernorm",
+    "model.vision_tower.encoder.layers.18.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.18.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.18.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.18.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.18.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.18.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.19.input_layernorm",
+    "model.vision_tower.encoder.layers.19.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.19.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.19.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.19.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.19.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.19.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.2.input_layernorm",
+    "model.vision_tower.encoder.layers.2.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.2.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.2.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.2.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.2.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.2.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.20.input_layernorm",
+    "model.vision_tower.encoder.layers.20.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.20.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.20.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.20.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.20.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.20.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.21.input_layernorm",
+    "model.vision_tower.encoder.layers.21.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.21.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.21.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.21.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.21.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.21.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.22.input_layernorm",
+    "model.vision_tower.encoder.layers.22.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.22.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.22.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.22.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.22.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.22.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.23.input_layernorm",
+    "model.vision_tower.encoder.layers.23.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.23.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.23.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.23.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.23.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.23.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.24.input_layernorm",
+    "model.vision_tower.encoder.layers.24.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.24.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.24.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.24.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.24.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.24.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.25.input_layernorm",
+    "model.vision_tower.encoder.layers.25.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.25.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.25.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.25.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.25.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.25.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.26.input_layernorm",
+    "model.vision_tower.encoder.layers.26.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.26.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.26.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.26.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.26.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.26.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.3.input_layernorm",
+    "model.vision_tower.encoder.layers.3.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.3.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.3.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.3.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.3.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.3.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.4.input_layernorm",
+    "model.vision_tower.encoder.layers.4.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.4.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.4.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.4.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.4.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.4.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.5.input_layernorm",
+    "model.vision_tower.encoder.layers.5.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.5.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.5.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.5.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.5.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.5.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.6.input_layernorm",
+    "model.vision_tower.encoder.layers.6.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.6.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.6.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.6.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.6.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.6.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.7.input_layernorm",
+    "model.vision_tower.encoder.layers.7.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.7.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.7.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.7.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.7.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.7.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.8.input_layernorm",
+    "model.vision_tower.encoder.layers.8.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.8.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.8.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.8.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.8.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.8.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear",
+    "model.vision_tower.encoder.layers.9.input_layernorm",
+    "model.vision_tower.encoder.layers.9.mlp.down_proj.linear",
+    "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear",
+    "model.vision_tower.encoder.layers.9.mlp.up_proj.linear",
+    "model.vision_tower.encoder.layers.9.post_attention_layernorm",
+    "model.vision_tower.encoder.layers.9.post_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm",
+    "model.vision_tower.encoder.layers.9.self_attn.k_norm",
+    "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear",
+    "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear",
+    "model.vision_tower.encoder.layers.9.self_attn.q_norm",
+    "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear",
+    "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear",
+    "model.vision_tower.patch_embedder.input_proj"
+  ],
+  "provider": "auto-round"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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",
+  "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>"
+}