Instructions to use zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6")
config = load_config("zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

zecanard commited on Jun 11

Commit

55046aa

verified ·

1 Parent(s): 2875799

Add files using upload-large-folder tool

Browse files

Files changed (11) hide show

.gitattributes +1 -0
README.md +45 -0
chat_template.jinja +368 -0
config.json +3003 -0
generation_config.json +14 -0
model-00001-of-00002.safetensors +3 -0
model-00002-of-00002.safetensors +3 -0
model.safetensors.index.json +0 -0
processor_config.json +41 -0
tokenizer.json +3 -0
tokenizer_config.json +99 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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 ADDED Viewed

	@@ -0,0 +1,45 @@

+---
+license: gemma
+base_model: wangzhang/gemma-4-E4B-it-abliterix
+language: en
+pipeline_tag: image-text-to-text
+library_name: mlx
+tags:
+  - mlx
+  - 3-bit
+  - abliterix
+  - decensored
+  - abliterated
+  - uncensored
+  - gemma4
+  - direct-weight-editing
+  - multimodal
+---
+# 🦆 zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6
+[This model](https://huggingface.co/zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6) was converted to MLX from [`wangzhang/gemma-4-E4B-it-abliterix`](https://huggingface.co/wangzhang/gemma-4-E4B-it-abliterix) using `mlx-vlm` version **0.6.3**.
+Please refer to the [original model card](https://huggingface.co/wangzhang/gemma-4-E4B-it-abliterix) for more details.
+## 🌟 Quality
+Mixed-precision quantized vision language model with an effective **5.804 bits per weight**. Combines the size and speed benefits of a 3-bit quant with higher precision where it matters most.
+`mlx_vlm.convert --quantize --q-group-size 32 --quant-predicate mixed_3_6`
+## 🛠️ Customizations
+This quant is aware of the current date, and also enables thinking (if available). You may disable this behavior by deleting the following line from the chat template, or changing `true` to `false`:
+`{%- set enable_thinking = true %}`
+You may also need to adjust your environment’s **Reasoning Section Parsing** to recognize `<|channel>thought` as the **Start String**, and `<channel|>` as the **End String**.
+## 🖥️ Use with `mlx`
+```bash
+pip install -U mlx-vlm
+```
+```bash
+mlx_vlm.generate --model zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-3bit-mixed_3_6 --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image>
+```

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,368 @@

+{#- Template customizations by @zecanard. #}
+{%- set enable_thinking = true %}
+{%- set preserve_thinking = true %}
+{%- if strftime_now is defined %}
+	{%- set currentDate = strftime_now('%Y-%m-%d %G:%i:%s') %}
+{%- elif not currentDate is defined %}
+	{%- set currentDate = '2026-06-11' %}
+{%- endif %}
+{{- 'The current date is: ' + currentDate + ".\n\n" }}
+{#- Template customizations by @zecanard. #}
+{%- 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['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([])) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro format_type_argument(type_value) -%}
+    {%- if type_value is string -%}
+        {{- type_value | lower -}}
+    {%- elif type_value is iterable -%}
+        {{- '[' -}}
+        {%- for t in type_value -%}
+            {{- t | lower -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- type_value -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {{- 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 %}
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
+    {%- set prev_nt = namespace(role=None, found=false) -%}
+    {%- if loop.index0 > 0 -%}
+        {%- for j in range(loop.index0 - 1, -1, -1) -%}
+            {%- if not prev_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
+                    {%- set prev_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['tool_calls'] -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
+                        {%- for tc in message['tool_calls'] -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                        {%- 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 -%}
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '<|image|>' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '<|video|>' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not message.get('content')) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json ADDED Viewed

	@@ -0,0 +1,3003 @@

+{
+    "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,
+    "do_sample": true,
+    "dtype": "bfloat16",
+    "eoa_token_id": 258883,
+    "eoa_token_index": 258883,
+    "eoi_token_id": 258882,
+    "eos_token_id": [
+        1,
+        106,
+        50
+    ],
+    "generation_config": {
+        "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": "5.6.0.dev0"
+    },
+    "image_token_id": 258880,
+    "initializer_range": 0.02,
+    "model_type": "gemma4",
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.40.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.41.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.embed_tokens_per_layer": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.per_layer_model_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "embed_vision.embedding_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "embed_audio.embedding_projection": {
+            "group_size": 64,
+            "bits": 3
+        }
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.0.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.1.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.2.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.3.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.4.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.5.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.6.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.7.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.8.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.9.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.10.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.11.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.12.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.13.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.14.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.15.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.16.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.17.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.18.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.19.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.20.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.21.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.22.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.23.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.24.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.25.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.26.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.27.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.28.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.28.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.29.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.30.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.31.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.31.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.32.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.33.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.34.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.34.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.35.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.36.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.36.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.37.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.37.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.38.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.38.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.39.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.39.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.40.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.40.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.layers.41.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.per_layer_input_gate": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.layers.41.per_layer_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "language_model.model.embed_tokens_per_layer": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "language_model.model.per_layer_model_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "embed_vision.embedding_projection": {
+            "group_size": 64,
+            "bits": 3
+        },
+        "embed_audio.embedding_projection": {
+            "group_size": 64,
+            "bits": 3
+        }
+    },
+    "temperature": 1.0,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_k_eq_v": false,
+        "bos_token_id": 2,
+        "dtype": "bfloat16",
+        "enable_moe_block": false,
+        "eos_token_id": 1,
+        "expert_intermediate_size": null,
+        "final_logit_softcapping": 30.0,
+        "global_head_dim": 512,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2560,
+        "hidden_size_per_layer_input": 256,
+        "initializer_range": 0.02,
+        "intermediate_size": 10240,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_text",
+        "moe_intermediate_size": null,
+        "num_attention_heads": 8,
+        "num_experts": null,
+        "num_global_key_value_heads": null,
+        "num_hidden_layers": 42,
+        "num_key_value_heads": 2,
+        "num_kv_shared_layers": 18,
+        "pad_token_id": 0,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "full_attention": {
+                "partial_rotary_factor": 0.25,
+                "rope_theta": 1000000.0,
+                "rope_type": "proportional"
+            },
+            "sliding_attention": {
+                "rope_theta": 10000.0,
+                "rope_type": "default"
+            }
+        },
+        "sliding_window": 512,
+        "tie_word_embeddings": true,
+        "top_k_experts": null,
+        "use_bidirectional_attention": null,
+        "use_cache": true,
+        "use_double_wide_mlp": false,
+        "vocab_size": 262144,
+        "vocab_size_per_layer_input": 262144
+    },
+    "tie_word_embeddings": true,
+    "top_k": 64,
+    "top_p": 0.95,
+    "transformers_version": "5.6.0.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
+}

generation_config.json ADDED Viewed

	@@ -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": "5.6.0.dev0"
+}

model-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c54fbd2a3f7c7dba7caa0b5f02b571bb598d867c6f5b1d34231768c956594321
+size 5367878626

model-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:400b797a742365a9bbe9535602339d5836da262612ef87eecb5ba856ba6ab9d8
+size 365844952

model.safetensors.index.json ADDED Viewed

The diff for this file is too large to render. See raw diff

processor_config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "audio_seq_length": 750,
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 224,
+      "width": 224
+    }
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "feature_extractor": {
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "sampling_rate": 16000,
+    "num_mel_filters": 128,
+    "fft_length": 512,
+    "hop_length": 160,
+    "chunk_duration": 8.0,
+    "overlap_duration": 1.0
+  },
+  "audio_ms_per_token": 40
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2619fe11b50dbed06ac443c51d757b354d0b62d64baa514404d4e84e6713519
+size 32169780

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,99 @@

+{
+  "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": true,
+  "local_files_only": true,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "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_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "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>"
+}