Upload folder using huggingface_hub

.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 +1,69 @@
+---
+license: gemma
+base_model: google/gemma-4-E4B-it
+tags:
+  - fp8
+  - quantized
+  - gemma4
+  - protoLabsAI
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# gemma-4-E4B-it-FP8
+
+FP8 quantized version of [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it), produced by [protoLabsAI](https://huggingface.co/protoLabsAI).
+
+## Quantization Details
+
+| Property | Value |
+|----------|-------|
+| Base model | google/gemma-4-E4B-it |
+| Quant method | Native FP8 (float8_e4m3fn) |
+| Weight scheme | Per-block (128×128) |
+| Activation scheme | Dynamic |
+| Modules skipped | embed_tokens, lm_head, norms, visual encoder |
+
+## Benchmarks (RTX PRO 6000 Blackwell)
+
+Evaluated on protoLabs eval suite (quick profile: 10 claw-eval tasks + 9 custom suites + 8 function-call tests).
+
+**gemma-4-26B-A4B-it (MoE, 4B active):**
+
+| Config | Decode | TTFT | VRAM | Context | Claw Avg | Custom | FC |
+|--------|:------:|:----:|:----:|:-------:|:--------:|:------:|:--:|
+| BF16 1×GPU | 141 tok/s | 52ms | 48.5 GiB | 32K | 0.626 | 9/9 | 8/8 |
+| FP8 1×GPU | 173 tok/s | 83ms | 25.7 GiB | 32K | 0.634 | 9/9 | 8/8 |
+| FP8 TP=2 | 208 tok/s | 254ms | ~13 GiB/GPU | 65K | — | — | — |
+| FP8 TP=2 | 153 tok/s | 301ms | ~45 GiB/GPU | 256K | — | — | — |
+
+**No quality degradation from FP8 quantization** — FP8 scores marginally higher than BF16 (0.634 vs 0.626).
+
+## Usage with vLLM
+
+```bash
+# On-the-fly FP8 (recommended — loads BF16 weights, quantizes at load time)
+vllm serve google/gemma-4-26B-A4B-it \
+  --quantization fp8 \
+  --max-model-len 32768 \
+  --enable-auto-tool-choice \
+  --tool-call-parser gemma4
+
+# Or use these pre-quantized weights directly
+vllm serve protoLabsAI/gemma-4-E4B-it-FP8 \
+  --max-model-len 32768
+
+# TP=2 for 256K context
+vllm serve google/gemma-4-26B-A4B-it \
+  --quantization fp8 --kv-cache-dtype fp8 \
+  --tensor-parallel-size 2 \
+  --max-model-len 262144
+```
+
+**Requires vLLM built from main** (>= commit 08ed2b968, PR #38826) — Gemma 4 support not yet in a release.
+
+## Produced By
+
+[protoLabsAI](https://github.com/protoLabsAI) — AI inference node running 2× RTX PRO 6000 Blackwell (192 GB VRAM).
+
+Quantization pipeline: [protoLabsAI/lab/experiments/quantize](https://github.com/protoLabsAI/lab/tree/main/experiments/quantize)

chat_template.jinja

@@ -0,0 +1,263 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{ bos_token }}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {{- messages[0]['content'] | trim -}}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+        {{- '<|turn>' + role + '\n' }}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['tool_calls'] -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- if message['tool_responses'] -%}
+                {#- Tool Response handling -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- '<|tool_response>' -}}
+                    {%- if tool_response['response'] is mapping -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}
+                        {%- for key, value in tool_response['response'] | dictsort -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- if not loop.last %},{% endif -%}
+                        {%- endfor -%}
+                        {{- '}' -}}
+                    {%- else -%}
+                        {{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}
+                    {%- endif -%}
+                    {{- '<tool_response|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_response' -%}
+            {%- endif -%}
+
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '\n\n<|image|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '\n\n<|video|>\n\n' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+        {%- if not (message['tool_responses'] and not message['content']) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,713 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280,
+  "quantization_config": {
+    "quant_method": "fp8",
+    "activation_scheme": "dynamic",
+    "weight_per_tensor": false,
+    "act_per_tensor": false,
+    "weight_block_size": [
+      128,
+      128
+    ],
+    "modules_to_not_convert": [
+      "model.audio_tower.layers.0.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.0.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.0.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.0.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.0.lconv1d.conv_norm",
+      "model.audio_tower.layers.0.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.0.norm_out",
+      "model.audio_tower.layers.0.norm_post_attn",
+      "model.audio_tower.layers.0.norm_pre_attn",
+      "model.audio_tower.layers.1.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.1.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.1.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.1.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.1.lconv1d.conv_norm",
+      "model.audio_tower.layers.1.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.1.norm_out",
+      "model.audio_tower.layers.1.norm_post_attn",
+      "model.audio_tower.layers.1.norm_pre_attn",
+      "model.audio_tower.layers.10.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.10.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.10.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.10.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.10.lconv1d.conv_norm",
+      "model.audio_tower.layers.10.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.10.norm_out",
+      "model.audio_tower.layers.10.norm_post_attn",
+      "model.audio_tower.layers.10.norm_pre_attn",
+      "model.audio_tower.layers.11.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.11.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.11.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.11.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.11.lconv1d.conv_norm",
+      "model.audio_tower.layers.11.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.11.norm_out",
+      "model.audio_tower.layers.11.norm_post_attn",
+      "model.audio_tower.layers.11.norm_pre_attn",
+      "model.audio_tower.layers.2.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.2.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.2.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.2.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.2.lconv1d.conv_norm",
+      "model.audio_tower.layers.2.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.2.norm_out",
+      "model.audio_tower.layers.2.norm_post_attn",
+      "model.audio_tower.layers.2.norm_pre_attn",
+      "model.audio_tower.layers.3.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.3.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.3.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.3.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.3.lconv1d.conv_norm",
+      "model.audio_tower.layers.3.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.3.norm_out",
+      "model.audio_tower.layers.3.norm_post_attn",
+      "model.audio_tower.layers.3.norm_pre_attn",
+      "model.audio_tower.layers.4.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.4.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.4.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.4.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.4.lconv1d.conv_norm",
+      "model.audio_tower.layers.4.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.4.norm_out",
+      "model.audio_tower.layers.4.norm_post_attn",
+      "model.audio_tower.layers.4.norm_pre_attn",
+      "model.audio_tower.layers.5.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.5.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.5.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.5.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.5.lconv1d.conv_norm",
+      "model.audio_tower.layers.5.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.5.norm_out",
+      "model.audio_tower.layers.5.norm_post_attn",
+      "model.audio_tower.layers.5.norm_pre_attn",
+      "model.audio_tower.layers.6.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.6.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.6.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.6.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.6.lconv1d.conv_norm",
+      "model.audio_tower.layers.6.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.6.norm_out",
+      "model.audio_tower.layers.6.norm_post_attn",
+      "model.audio_tower.layers.6.norm_pre_attn",
+      "model.audio_tower.layers.7.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.7.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.7.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.7.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.7.lconv1d.conv_norm",
+      "model.audio_tower.layers.7.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.7.norm_out",
+      "model.audio_tower.layers.7.norm_post_attn",
+      "model.audio_tower.layers.7.norm_pre_attn",
+      "model.audio_tower.layers.8.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.8.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.8.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.8.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.8.lconv1d.conv_norm",
+      "model.audio_tower.layers.8.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.8.norm_out",
+      "model.audio_tower.layers.8.norm_post_attn",
+      "model.audio_tower.layers.8.norm_pre_attn",
+      "model.audio_tower.layers.9.feed_forward1.post_layer_norm",
+      "model.audio_tower.layers.9.feed_forward1.pre_layer_norm",
+      "model.audio_tower.layers.9.feed_forward2.post_layer_norm",
+      "model.audio_tower.layers.9.feed_forward2.pre_layer_norm",
+      "model.audio_tower.layers.9.lconv1d.conv_norm",
+      "model.audio_tower.layers.9.lconv1d.pre_layer_norm",
+      "model.audio_tower.layers.9.norm_out",
+      "model.audio_tower.layers.9.norm_post_attn",
+      "model.audio_tower.layers.9.norm_pre_attn",
+      "model.audio_tower.subsample_conv_projection.layer0.norm",
+      "model.audio_tower.subsample_conv_projection.layer1.norm",
+      "model.language_model.embed_tokens",
+      "model.language_model.embed_tokens_per_layer",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.0.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.1.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.10.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.11.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.12.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.13.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.14.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.15.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.16.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.17.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.18.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.19.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.2.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.20.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.21.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.22.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.23.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.24.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.25.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.26.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.27.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.28.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.29.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.3.pre_feedforward_layernorm",
+      "model.language_model.layers.3.self_attn.k_norm",
+      "model.language_model.layers.3.self_attn.q_norm",
+      "model.language_model.layers.30.input_layernorm",
+      "model.language_model.layers.30.post_attention_layernorm",
+      "model.language_model.layers.30.post_feedforward_layernorm",
+      "model.language_model.layers.30.post_per_layer_input_norm",
+      "model.language_model.layers.30.pre_feedforward_layernorm",
+      "model.language_model.layers.30.self_attn.k_norm",
+      "model.language_model.layers.30.self_attn.q_norm",
+      "model.language_model.layers.31.input_layernorm",
+      "model.language_model.layers.31.post_attention_layernorm",
+      "model.language_model.layers.31.post_feedforward_layernorm",
+      "model.language_model.layers.31.post_per_layer_input_norm",
+      "model.language_model.layers.31.pre_feedforward_layernorm",
+      "model.language_model.layers.31.self_attn.k_norm",
+      "model.language_model.layers.31.self_attn.q_norm",
+      "model.language_model.layers.32.input_layernorm",
+      "model.language_model.layers.32.post_attention_layernorm",
+      "model.language_model.layers.32.post_feedforward_layernorm",
+      "model.language_model.layers.32.post_per_layer_input_norm",
+      "model.language_model.layers.32.pre_feedforward_layernorm",
+      "model.language_model.layers.32.self_attn.k_norm",
+      "model.language_model.layers.32.self_attn.q_norm",
+      "model.language_model.layers.33.input_layernorm",
+      "model.language_model.layers.33.post_attention_layernorm",
+      "model.language_model.layers.33.post_feedforward_layernorm",
+      "model.language_model.layers.33.post_per_layer_input_norm",
+      "model.language_model.layers.33.pre_feedforward_layernorm",
+      "model.language_model.layers.33.self_attn.k_norm",
+      "model.language_model.layers.33.self_attn.q_norm",
+      "model.language_model.layers.34.input_layernorm",
+      "model.language_model.layers.34.post_attention_layernorm",
+      "model.language_model.layers.34.post_feedforward_layernorm",
+      "model.language_model.layers.34.post_per_layer_input_norm",
+      "model.language_model.layers.34.pre_feedforward_layernorm",
+      "model.language_model.layers.34.self_attn.k_norm",
+      "model.language_model.layers.34.self_attn.q_norm",
+      "model.language_model.layers.35.input_layernorm",
+      "model.language_model.layers.35.post_attention_layernorm",
+      "model.language_model.layers.35.post_feedforward_layernorm",
+      "model.language_model.layers.35.post_per_layer_input_norm",
+      "model.language_model.layers.35.pre_feedforward_layernorm",
+      "model.language_model.layers.35.self_attn.k_norm",
+      "model.language_model.layers.35.self_attn.q_norm",
+      "model.language_model.layers.36.input_layernorm",
+      "model.language_model.layers.36.post_attention_layernorm",
+      "model.language_model.layers.36.post_feedforward_layernorm",
+      "model.language_model.layers.36.post_per_layer_input_norm",
+      "model.language_model.layers.36.pre_feedforward_layernorm",
+      "model.language_model.layers.36.self_attn.k_norm",
+      "model.language_model.layers.36.self_attn.q_norm",
+      "model.language_model.layers.37.input_layernorm",
+      "model.language_model.layers.37.post_attention_layernorm",
+      "model.language_model.layers.37.post_feedforward_layernorm",
+      "model.language_model.layers.37.post_per_layer_input_norm",
+      "model.language_model.layers.37.pre_feedforward_layernorm",
+      "model.language_model.layers.37.self_attn.k_norm",
+      "model.language_model.layers.37.self_attn.q_norm",
+      "model.language_model.layers.38.input_layernorm",
+      "model.language_model.layers.38.post_attention_layernorm",
+      "model.language_model.layers.38.post_feedforward_layernorm",
+      "model.language_model.layers.38.post_per_layer_input_norm",
+      "model.language_model.layers.38.pre_feedforward_layernorm",
+      "model.language_model.layers.38.self_attn.k_norm",
+      "model.language_model.layers.38.self_attn.q_norm",
+      "model.language_model.layers.39.input_layernorm",
+      "model.language_model.layers.39.post_attention_layernorm",
+      "model.language_model.layers.39.post_feedforward_layernorm",
+      "model.language_model.layers.39.post_per_layer_input_norm",
+      "model.language_model.layers.39.pre_feedforward_layernorm",
+      "model.language_model.layers.39.self_attn.k_norm",
+      "model.language_model.layers.39.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_per_layer_input_norm",
+      "model.language_model.layers.4.pre_feedforward_layernorm",
+      "model.language_model.layers.4.self_attn.k_norm",
+      "model.language_model.layers.4.self_attn.q_norm",
+      "model.language_model.layers.40.input_layernorm",
+      "model.language_model.layers.40.post_attention_layernorm",
+      "model.language_model.layers.40.post_feedforward_layernorm",
+      "model.language_model.layers.40.post_per_layer_input_norm",
+      "model.language_model.layers.40.pre_feedforward_layernorm",
+      "model.language_model.layers.40.self_attn.k_norm",
+      "model.language_model.layers.40.self_attn.q_norm",
+      "model.language_model.layers.41.input_layernorm",
+      "model.language_model.layers.41.post_attention_layernorm",
+      "model.language_model.layers.41.post_feedforward_layernorm",
+      "model.language_model.layers.41.post_per_layer_input_norm",
+      "model.language_model.layers.41.pre_feedforward_layernorm",
+      "model.language_model.layers.41.self_attn.k_norm",
+      "model.language_model.layers.41.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_per_layer_input_norm",
+      "model.language_model.layers.5.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.6.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.7.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.8.pre_feedforward_layernorm",
+      "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_per_layer_input_norm",
+      "model.language_model.layers.9.pre_feedforward_layernorm",
+      "model.language_model.layers.9.self_attn.k_norm",
+      "model.language_model.layers.9.self_attn.q_norm",
+      "model.language_model.norm",
+      "model.language_model.per_layer_projection_norm",
+      "model.vision_tower.encoder.layers.0.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.1.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.10.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.11.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.12.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.13.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.14.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.15.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.2.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.3.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.4.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.5.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.6.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.7.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.8.input_layernorm",
+      "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.q_norm",
+      "model.vision_tower.encoder.layers.9.input_layernorm",
+      "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.q_norm"
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106,
+    50
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c1c4057cb900125c5174828877c30a7623996d1a7326e9ef6236326a142315
+size 12846004452

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
+  },
+  "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>"
+}