Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,256 @@
+---
+license: other
+license_name: apache-2.0
+language:
+- en
+tags:
+- multimodal
+library_name: transformers
+pipeline_tag: any-to-any
+base_model: Qwen/Qwen3-Omni-30B-A3B-Captioner
+---
+
+# Qwen3-Omni
+
+<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+
+## Overview
+### Introduction
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/q3o_introduction.png" width="100%"/>
+<p>
+
+Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain **Qwen3-Omni-30B-A3B-Captioner**, which produces detailed, low-hallucination captions for arbitrary audio inputs.
+
+**Qwen3-Omni-30B-A3B-Captioner** is a powerful fine-grained audio analysis model, built upon the Qwen3-Omni-30B-A3B-Instruct base model. It is specifically designed to generate accurate and comprehensive content descriptions in complex and diverse audio scenarios. Without requiring any additional prompting, the model can automatically parse and describe various types of audio content, ranging from complex speech and environmental sounds to music and cinematic sound effects, delivering stable and reliable outputs even in multi-source, mixed audio environments.
+
+In terms of speech understanding, Qwen3-Omni-30B-A3B-Captioner excels at identifying multiple speaker emotions, multilingual expressions, and layered intentions. It can also perceive cultural context and implicit information within the audio, enabling a deep comprehension of the underlying meaning behind the spoken words. In non-speech scenarios, the model demonstrates exceptional sound recognition and analysis capabilities, accurately distinguishing and describing intricate layers of real-world sounds, ambient atmospheres, and dynamic audio details in film and media.
+
+**Note**: Qwen3-Omni-30B-A3B-Captioner is a single-turn model that accepts only one audio input per inference. It does not accept any text prompts and supports **audio input only**, with **text output only**. As Qwen3-Omni-30B-A3B-Captioner is designed for generating fine‑grained descriptions of audio, excessively long audio clips may diminish detail perception. We recommend, as a best practice, limiting audio length to no more than 30 seconds.
+
+## QuickStart
+
+### Model Description and Download
+
+| Model Name                   | Description |
+|------------------------------|-------------|
+| Qwen3-Omni-30B-A3B-Captioner | A downstream audio fine-grained caption model fine-tuned from Qwen3-Omni-30B-A3B-Instruct, which produces detailed, low-hallucination captions for arbitrary audio inputs. It contains the thinker, supporting audio input and text output. For more information, you can refer to the model's [cookbook](https://github.com/QwenLM/Qwen3-Omni/blob/main/cookbooks/omni_captioner.ipynb) or [Hugging Face Demo](https://huggingface.co/spaces/Qwen/Qwen3-Omni-Captioner-Demo) and [ModelScope Demo](https://modelscope.cn/studios/Qwen/Qwen3-Omni-Captioner-Demo). |
+
+During loading in Hugging Face Transformers or vLLM, model weights will be automatically downloaded based on the model name. However, if your runtime environment is not conducive to downloading weights during execution, you can refer to the following commands to manually download the model weights to a local directory:
+
+```bash
+# Download through ModelScope (recommended for users in Mainland China)
+pip install -U modelscope
+modelscope download --model Qwen/Qwen3-Omni-30B-A3B-Captioner --local_dir ./Qwen3-Omni-30B-A3B-Captioner
+
+# Download through Hugging Face
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download Qwen/Qwen3-Omni-30B-A3B-Captioner --local-dir ./Qwen3-Omni-30B-A3B-Captioner
+```
+
+### Transformers Usage
+
+#### Installation
+
+The Hugging Face Transformers code for Qwen3-Omni has been successfully merged, but the PyPI package has not yet been released. Therefore, you need to install it from source using the following command. We strongly recommend that you **create a new Python environment** to avoid environment runtime issues.
+
+```bash
+# If you already have transformers installed, please uninstall it first, or create a new Python environment
+# pip uninstall transformers
+pip install git+https://github.com/huggingface/transformers
+pip install accelerate
+```
+
+We offer a toolkit to help you handle various types of audio and visual input more conveniently, providing an API-like experience. This includes support for base64, URLs, and interleaved audio, images, and videos. You can install it using the following command and make sure your system has `ffmpeg` installed:
+
+```bash
+pip install qwen-omni-utils -U
+```
+
+Additionally, we recommend using FlashAttention 2 when running with Hugging Face Transformers to reduce GPU memory usage. However, if you are primarily using [vLLM](#vllm-usage) for inference, this installation is not necessary, as vLLM includes FlashAttention 2 by default.
+
+```bash
+pip install -U flash-attn --no-build-isolation
+```
+
+Also, you should have hardware that is compatible with FlashAttention 2. Read more about it in the official documentation of the [FlashAttention repository](https://github.com/Dao-AILab/flash-attention). FlashAttention 2 can only be used when a model is loaded in `torch.float16` or `torch.bfloat16`.
+
+#### Code Snippet
+
+Here is a code snippet to show you how to use Qwen3-Omni-30B-A3B-Captioner with `transformers` and `qwen_omni_utils`:
+
+```python
+import soundfile as sf
+
+from transformers import Qwen3OmniMoeForConditionalGeneration, Qwen3OmniMoeProcessor
+from qwen_omni_utils import process_mm_info
+
+MODEL_PATH = "Qwen/Qwen3-Omni-30B-A3B-Captioner"
+
+model = Qwen3OmniMoeForConditionalGeneration.from_pretrained(
+    MODEL_PATH,
+    dtype="auto",
+    device_map="auto",
+    attn_implementation="flash_attention_2",
+)
+
+processor = Qwen3OmniMoeProcessor.from_pretrained(MODEL_PATH)
+
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "audio", "audio": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/cookbook/caption2.mp3"},
+        ],
+    },
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
+audios, _, _ = process_mm_info(conversation, use_audio_in_video=False)
+inputs = processor(text=text, 
+                   audio=audios,
+                   return_tensors="pt", 
+                   padding=True, 
+                   use_audio_in_video=False)
+inputs = inputs.to(model.device).to(model.dtype)
+
+# Inference: Generation of the output text and audio
+text_ids, audio = model.generate(**inputs, 
+                                 thinker_return_dict_in_generate=True)
+
+text = processor.batch_decode(text_ids.sequences[:, inputs["input_ids"].shape[1] :],
+                              skip_special_tokens=True,
+                              clean_up_tokenization_spaces=False)
+print(text)
+```
+
+### vLLM Usage
+
+#### Installation
+
+We strongly recommend using vLLM for inference and deployment of the Qwen3-Omni series models. Since our code is currently in the pull request stage, you can follow the commands below to install vLLM from source. Please note that we recommend you **create a new Python environment** to avoid runtime environment conflicts and incompatibilities. For more details on compiling vLLM from source, please refer to the [vLLM official documentation](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#set-up-using-python-only-build-without-compilation).
+
+```bash
+git clone -b qwen3_omni https://github.com/wangxiongts/vllm.git
+cd vllm
+pip install -r requirements/build.txt
+pip install -r requirements/cuda.txt
+export VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/a5dd03c1ebc5e4f56f3c9d3dc0436e9c582c978f/vllm-0.9.2-cp38-abi3-manylinux1_x86_64.whl
+VLLM_USE_PRECOMPILED=1 pip install -e . -v --no-build-isolation
+# If you meet an "Undefined symbol" error while using VLLM_USE_PRECOMPILED=1, please use "pip install -e . -v" to build from source.
+# Install the Transformers
+pip install git+https://github.com/huggingface/transformers
+pip install accelerate
+pip install qwen-omni-utils -U
+pip install -U flash-attn --no-build-isolation
+```
+
+#### Inference
+
+Below is a simple example of how to run Qwen3-Omni-30B-A3B-Captioner with vLLM:
+
+```python
+import os
+import torch
+
+from vllm import LLM, SamplingParams
+from transformers import Qwen3OmniMoeProcessor
+from qwen_omni_utils import process_mm_info
+
+if __name__ == '__main__':
+    # vLLM engine v1 not supported yet
+    os.environ['VLLM_USE_V1'] = '0'
+
+    MODEL_PATH = "Qwen/Qwen3-Omni-30B-A3B-Captioner"
+
+    llm = LLM(
+            model=MODEL_PATH, trust_remote_code=True, gpu_memory_utilization=0.95,
+            tensor_parallel_size=torch.cuda.device_count(),
+            limit_mm_per_prompt={'audio': 1},
+            max_num_seqs=8,
+            max_model_len=32768,
+            seed=1234,
+    )
+
+    sampling_params = SamplingParams(
+        temperature=0.6,
+        top_p=0.95,
+        top_k=20,
+        max_tokens=16384,
+    )
+
+    processor = Qwen3OmniMoeProcessor.from_pretrained(MODEL_PATH)
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "audio", "audio": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/cookbook/caption2.mp3"}
+            ], 
+        }
+    ]
+
+    text = processor.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+    audios, _, _ = process_mm_info(messages, use_audio_in_video=False)
+
+    inputs = {
+        'prompt': text,
+        'multi_modal_data': {},
+    }
+
+    if audios is not None:
+        inputs['multi_modal_data']['audio'] = audios
+
+    outputs = llm.generate([inputs], sampling_params=sampling_params)
+
+    print(outputs[0].outputs[0].text)
+```
+
+#### vLLM Serve Usage
+
+You can start vLLM serve through the following command:
+
+```bash
+# Qwen3-Omni-30B-A3B-Captioner for single GPU
+vllm serve Qwen/Qwen3-Omni-30B-A3B-Captioner --port 8901 --host 127.0.0.1 --dtype bfloat16 --max-model-len 32768 --allowed-local-media-path / -tp 1
+# Qwen3-Omni-30B-A3B-Captioner for multi-GPU (example on 4 GPUs)
+vllm serve Qwen/Qwen3-Omni-30B-A3B-Captioner --port 8901 --host 127.0.0.1 --dtype bfloat16 --max-model-len 32768 --allowed-local-media-path / -tp 4
+```
+
+Then you can use the API as below (via curl, for example):
+```bash
+curl http://localhost:8901/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+    "messages": [
+    {"role": "user", "content": [
+        {"type": "audio_url", "audio_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/cookbook/caption2.mp3"}}
+    ]}
+    ]
+    }'
+```
+
+<!-- ## Citation
+
+If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
+
+
+```BibTeX
+@article{Qwen3-Omni,
+  title={Qwen3-Omni Technical Report},
+  author={Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu, Peng Wang, Mingkun Yang, Dayiheng Liu, Xingzhang Ren, Bo Zheng, Rui Men, Fan Zhou, Bowen Yu, Jianxin Yang, Le Yu, Jingren Zhou, Junyang Lin},
+  journal={arXiv preprint arXiv},
+  year={2025}
+}
+``` -->
+
+<br>

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<tts_pad>": 151671,
+  "<tts_text_bos>": 151672,
+  "<tts_text_bos_single>": 151674,
+  "<tts_text_eod>": 151673,
+  "<|audio_end|>": 151670,
+  "<|audio_pad|>": 151675,
+  "<|audio_start|>": 151669,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,105 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}{{- messages[0].content + '\n\n' }}{%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {{- '<|im_start|>system\n' +"<|vision_start|><|image_pad|><|vision_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
+                    {{- '<|im_start|>system\n' +"<|audio_start|><|audio_pad|><|audio_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {{- '<|im_start|>system\n' +"<|vision_start|><|video_pad|><|vision_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'text' %}
+                    {{- '<|im_start|>system\n' +content.text+ '<|im_end|>\n' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = namespace(text="") %}
+        {%- for mcontent in message.content %}
+            {%- if mcontent.type == 'image' or 'image' in mcontent or 'image_url' in mcontent %}
+                {%- set content.text = content.text~"<|vision_start|><|image_pad|><|vision_end|>" %}
+            {%- elif mcontent.type == 'audio' or 'audio' in mcontent or 'audio_url' in mcontent %}
+                {%- set content.text = content.text~"<|audio_start|><|audio_pad|><|audio_end|>" %}
+            {%- elif mcontent.type == 'video' or 'video' in mcontent %}
+                {%- set content.text = content.text~"<|vision_start|><|video_pad|><|vision_end|>" %}
+            {%- elif mcontent.type == 'text' %}
+                {%- set content.text = content.text~mcontent.text %}
+            {%- endif %}
+        {%- endfor %}
+        {%- set content = content.text %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = "" %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+            {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+    {%- endif %}
+    {%- if loop.index0 > ns.last_query_index %}
+        {%- if loop.last or (not loop.last and reasoning_content) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip("\n") + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+    {%- endif %}
+    {%- if message.tool_calls %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if (loop.first and content) or (not loop.first) %}{{- '\n' }}{%- endif %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {%- if tool_call.arguments is string %}
+                {{- tool_call.arguments }}
+            {%- else %}
+                {{- tool_call.arguments | tojson }}
+            {%- endif %}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}{{- '<think>\n\n</think>\n\n' }}{%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,692 @@
+{
+  "architectures": [
+    "Qwen3OmniMoeForConditionalGeneration"
+  ],
+  "assistant_token_id": 77091,
+  "dtype": "bfloat16",
+  "enable_audio_output": false,
+  "im_end_token_id": 151645,
+  "im_start_token_id": 151644,
+  "model_type": "qwen3_omni_moe",
+  "system_token_id": 8948,
+  "thinker_config": {
+    "audio_config": {
+      "_name_or_path": "",
+      "activation_dropout": 0,
+      "activation_function": "gelu",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "conv_chunksize": 500,
+      "cross_attention_hidden_size": null,
+      "d_model": 1280,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "downsample_hidden_size":480,
+      "dropout": 0,
+      "dtype": null,
+      "early_stopping": false,
+      "encoder_attention_heads": 20,
+      "encoder_ffn_dim": 5120,
+      "encoder_layers": 32,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_source_positions": 1500,
+      "min_length": 0,
+      "model_type": "qwen3_omni_moe_audio_encoder",
+      "n_window": 50,
+      "n_window_infer": 800,
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 32,
+      "num_mel_bins": 128,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_dim": 2048,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "scale_embedding": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "audio_end_token_id": 151670,
+    "audio_start_token_id": 151669,
+    "audio_token_id": 151675,
+    "dtype": "bfloat16",
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "model_type": "qwen3_omni_moe_thinker",
+    "position_id_per_seconds": 13,
+    "seconds_per_chunk": 2,
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_sparse_step": 1,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": true,
+      "dtype": null,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 768,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 65536,
+      "min_length": 0,
+      "mlp_only_layers": [],
+      "model_type": "qwen3_omni_moe_text",
+      "moe_intermediate_size": 768,
+      "no_repeat_ngram_size": 0,
+      "norm_topk_prob": true,
+      "num_attention_heads": 32,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_experts": 128,
+      "num_experts_per_tok": 8,
+      "num_hidden_layers": 48,
+      "num_key_value_heads": 4,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_router_logits": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "interleaved": true,
+        "mrope_interleaved": true,
+        "mrope_section": [
+          24,
+          20,
+          20
+        ],
+        "rope_type": "default",
+        "type": "default"
+      },
+      "rope_theta": 1000000,
+      "router_aux_loss_coef": 0.001,
+      "sep_token_id": null,
+      "shared_expert_intermediate_size": 0,
+      "sliding_window": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_qk_norm": true,
+      "use_sliding_window": false,
+      "vocab_size": 152064
+    },
+    "user_token_id": 872,
+    "video_token_id": 151656,
+    "vision_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "apply_vit_abs_pos_embed": true,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "deepstack_visual_indexes": [
+        8,
+        16,
+        24
+      ],
+      "depth": 27,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": null,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 768,
+      "in_channels": 3,
+      "in_chans": 3,
+      "initializer_range": 0.02,
+      "intermediate_size": 4304,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "qwen3_omni_moe_vision_encoder",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_heads": 16,
+      "num_return_sequences": 1,
+      "out_hidden_size": 2048,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 16,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 16,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "tokens_per_second": 2,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652
+  },
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 4,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "thinker.audio_tower.layers.0.self_attn.k_proj",
+      "thinker.audio_tower.layers.0.self_attn.v_proj",
+      "thinker.audio_tower.layers.0.self_attn.q_proj",
+      "thinker.audio_tower.layers.0.self_attn.out_proj",
+      "thinker.audio_tower.layers.0.fc1",
+      "thinker.audio_tower.layers.0.fc2",
+      "thinker.audio_tower.layers.1.self_attn.k_proj",
+      "thinker.audio_tower.layers.1.self_attn.v_proj",
+      "thinker.audio_tower.layers.1.self_attn.q_proj",
+      "thinker.audio_tower.layers.1.self_attn.out_proj",
+      "thinker.audio_tower.layers.1.fc1",
+      "thinker.audio_tower.layers.1.fc2",
+      "thinker.audio_tower.layers.2.self_attn.k_proj",
+      "thinker.audio_tower.layers.2.self_attn.v_proj",
+      "thinker.audio_tower.layers.2.self_attn.q_proj",
+      "thinker.audio_tower.layers.2.self_attn.out_proj",
+      "thinker.audio_tower.layers.2.fc1",
+      "thinker.audio_tower.layers.2.fc2",
+      "thinker.audio_tower.layers.3.self_attn.k_proj",
+      "thinker.audio_tower.layers.3.self_attn.v_proj",
+      "thinker.audio_tower.layers.3.self_attn.q_proj",
+      "thinker.audio_tower.layers.3.self_attn.out_proj",
+      "thinker.audio_tower.layers.3.fc1",
+      "thinker.audio_tower.layers.3.fc2",
+      "thinker.audio_tower.layers.4.self_attn.k_proj",
+      "thinker.audio_tower.layers.4.self_attn.v_proj",
+      "thinker.audio_tower.layers.4.self_attn.q_proj",
+      "thinker.audio_tower.layers.4.self_attn.out_proj",
+      "thinker.audio_tower.layers.4.fc1",
+      "thinker.audio_tower.layers.4.fc2",
+      "thinker.audio_tower.layers.5.self_attn.k_proj",
+      "thinker.audio_tower.layers.5.self_attn.v_proj",
+      "thinker.audio_tower.layers.5.self_attn.q_proj",
+      "thinker.audio_tower.layers.5.self_attn.out_proj",
+      "thinker.audio_tower.layers.5.fc1",
+      "thinker.audio_tower.layers.5.fc2",
+      "thinker.audio_tower.layers.6.self_attn.k_proj",
+      "thinker.audio_tower.layers.6.self_attn.v_proj",
+      "thinker.audio_tower.layers.6.self_attn.q_proj",
+      "thinker.audio_tower.layers.6.self_attn.out_proj",
+      "thinker.audio_tower.layers.6.fc1",
+      "thinker.audio_tower.layers.6.fc2",
+      "thinker.audio_tower.layers.7.self_attn.k_proj",
+      "thinker.audio_tower.layers.7.self_attn.v_proj",
+      "thinker.audio_tower.layers.7.self_attn.q_proj",
+      "thinker.audio_tower.layers.7.self_attn.out_proj",
+      "thinker.audio_tower.layers.7.fc1",
+      "thinker.audio_tower.layers.7.fc2",
+      "thinker.audio_tower.layers.8.self_attn.k_proj",
+      "thinker.audio_tower.layers.8.self_attn.v_proj",
+      "thinker.audio_tower.layers.8.self_attn.q_proj",
+      "thinker.audio_tower.layers.8.self_attn.out_proj",
+      "thinker.audio_tower.layers.8.fc1",
+      "thinker.audio_tower.layers.8.fc2",
+      "thinker.audio_tower.layers.9.self_attn.k_proj",
+      "thinker.audio_tower.layers.9.self_attn.v_proj",
+      "thinker.audio_tower.layers.9.self_attn.q_proj",
+      "thinker.audio_tower.layers.9.self_attn.out_proj",
+      "thinker.audio_tower.layers.9.fc1",
+      "thinker.audio_tower.layers.9.fc2",
+      "thinker.audio_tower.layers.10.self_attn.k_proj",
+      "thinker.audio_tower.layers.10.self_attn.v_proj",
+      "thinker.audio_tower.layers.10.self_attn.q_proj",
+      "thinker.audio_tower.layers.10.self_attn.out_proj",
+      "thinker.audio_tower.layers.10.fc1",
+      "thinker.audio_tower.layers.10.fc2",
+      "thinker.audio_tower.layers.11.self_attn.k_proj",
+      "thinker.audio_tower.layers.11.self_attn.v_proj",
+      "thinker.audio_tower.layers.11.self_attn.q_proj",
+      "thinker.audio_tower.layers.11.self_attn.out_proj",
+      "thinker.audio_tower.layers.11.fc1",
+      "thinker.audio_tower.layers.11.fc2",
+      "thinker.audio_tower.layers.12.self_attn.k_proj",
+      "thinker.audio_tower.layers.12.self_attn.v_proj",
+      "thinker.audio_tower.layers.12.self_attn.q_proj",
+      "thinker.audio_tower.layers.12.self_attn.out_proj",
+      "thinker.audio_tower.layers.12.fc1",
+      "thinker.audio_tower.layers.12.fc2",
+      "thinker.audio_tower.layers.13.self_attn.k_proj",
+      "thinker.audio_tower.layers.13.self_attn.v_proj",
+      "thinker.audio_tower.layers.13.self_attn.q_proj",
+      "thinker.audio_tower.layers.13.self_attn.out_proj",
+      "thinker.audio_tower.layers.13.fc1",
+      "thinker.audio_tower.layers.13.fc2",
+      "thinker.audio_tower.layers.14.self_attn.k_proj",
+      "thinker.audio_tower.layers.14.self_attn.v_proj",
+      "thinker.audio_tower.layers.14.self_attn.q_proj",
+      "thinker.audio_tower.layers.14.self_attn.out_proj",
+      "thinker.audio_tower.layers.14.fc1",
+      "thinker.audio_tower.layers.14.fc2",
+      "thinker.audio_tower.layers.15.self_attn.k_proj",
+      "thinker.audio_tower.layers.15.self_attn.v_proj",
+      "thinker.audio_tower.layers.15.self_attn.q_proj",
+      "thinker.audio_tower.layers.15.self_attn.out_proj",
+      "thinker.audio_tower.layers.15.fc1",
+      "thinker.audio_tower.layers.15.fc2",
+      "thinker.audio_tower.layers.16.self_attn.k_proj",
+      "thinker.audio_tower.layers.16.self_attn.v_proj",
+      "thinker.audio_tower.layers.16.self_attn.q_proj",
+      "thinker.audio_tower.layers.16.self_attn.out_proj",
+      "thinker.audio_tower.layers.16.fc1",
+      "thinker.audio_tower.layers.16.fc2",
+      "thinker.audio_tower.layers.17.self_attn.k_proj",
+      "thinker.audio_tower.layers.17.self_attn.v_proj",
+      "thinker.audio_tower.layers.17.self_attn.q_proj",
+      "thinker.audio_tower.layers.17.self_attn.out_proj",
+      "thinker.audio_tower.layers.17.fc1",
+      "thinker.audio_tower.layers.17.fc2",
+      "thinker.audio_tower.layers.18.self_attn.k_proj",
+      "thinker.audio_tower.layers.18.self_attn.v_proj",
+      "thinker.audio_tower.layers.18.self_attn.q_proj",
+      "thinker.audio_tower.layers.18.self_attn.out_proj",
+      "thinker.audio_tower.layers.18.fc1",
+      "thinker.audio_tower.layers.18.fc2",
+      "thinker.audio_tower.layers.19.self_attn.k_proj",
+      "thinker.audio_tower.layers.19.self_attn.v_proj",
+      "thinker.audio_tower.layers.19.self_attn.q_proj",
+      "thinker.audio_tower.layers.19.self_attn.out_proj",
+      "thinker.audio_tower.layers.19.fc1",
+      "thinker.audio_tower.layers.19.fc2",
+      "thinker.audio_tower.layers.20.self_attn.k_proj",
+      "thinker.audio_tower.layers.20.self_attn.v_proj",
+      "thinker.audio_tower.layers.20.self_attn.q_proj",
+      "thinker.audio_tower.layers.20.self_attn.out_proj",
+      "thinker.audio_tower.layers.20.fc1",
+      "thinker.audio_tower.layers.20.fc2",
+      "thinker.audio_tower.layers.21.self_attn.k_proj",
+      "thinker.audio_tower.layers.21.self_attn.v_proj",
+      "thinker.audio_tower.layers.21.self_attn.q_proj",
+      "thinker.audio_tower.layers.21.self_attn.out_proj",
+      "thinker.audio_tower.layers.21.fc1",
+      "thinker.audio_tower.layers.21.fc2",
+      "thinker.audio_tower.layers.22.self_attn.k_proj",
+      "thinker.audio_tower.layers.22.self_attn.v_proj",
+      "thinker.audio_tower.layers.22.self_attn.q_proj",
+      "thinker.audio_tower.layers.22.self_attn.out_proj",
+      "thinker.audio_tower.layers.22.fc1",
+      "thinker.audio_tower.layers.22.fc2",
+      "thinker.audio_tower.layers.23.self_attn.k_proj",
+      "thinker.audio_tower.layers.23.self_attn.v_proj",
+      "thinker.audio_tower.layers.23.self_attn.q_proj",
+      "thinker.audio_tower.layers.23.self_attn.out_proj",
+      "thinker.audio_tower.layers.23.fc1",
+      "thinker.audio_tower.layers.23.fc2",
+      "thinker.audio_tower.layers.24.self_attn.k_proj",
+      "thinker.audio_tower.layers.24.self_attn.v_proj",
+      "thinker.audio_tower.layers.24.self_attn.q_proj",
+      "thinker.audio_tower.layers.24.self_attn.out_proj",
+      "thinker.audio_tower.layers.24.fc1",
+      "thinker.audio_tower.layers.24.fc2",
+      "thinker.audio_tower.layers.25.self_attn.k_proj",
+      "thinker.audio_tower.layers.25.self_attn.v_proj",
+      "thinker.audio_tower.layers.25.self_attn.q_proj",
+      "thinker.audio_tower.layers.25.self_attn.out_proj",
+      "thinker.audio_tower.layers.25.fc1",
+      "thinker.audio_tower.layers.25.fc2",
+      "thinker.audio_tower.layers.26.self_attn.k_proj",
+      "thinker.audio_tower.layers.26.self_attn.v_proj",
+      "thinker.audio_tower.layers.26.self_attn.q_proj",
+      "thinker.audio_tower.layers.26.self_attn.out_proj",
+      "thinker.audio_tower.layers.26.fc1",
+      "thinker.audio_tower.layers.26.fc2",
+      "thinker.audio_tower.layers.27.self_attn.k_proj",
+      "thinker.audio_tower.layers.27.self_attn.v_proj",
+      "thinker.audio_tower.layers.27.self_attn.q_proj",
+      "thinker.audio_tower.layers.27.self_attn.out_proj",
+      "thinker.audio_tower.layers.27.fc1",
+      "thinker.audio_tower.layers.27.fc2",
+      "thinker.audio_tower.layers.28.self_attn.k_proj",
+      "thinker.audio_tower.layers.28.self_attn.v_proj",
+      "thinker.audio_tower.layers.28.self_attn.q_proj",
+      "thinker.audio_tower.layers.28.self_attn.out_proj",
+      "thinker.audio_tower.layers.28.fc1",
+      "thinker.audio_tower.layers.28.fc2",
+      "thinker.audio_tower.layers.29.self_attn.k_proj",
+      "thinker.audio_tower.layers.29.self_attn.v_proj",
+      "thinker.audio_tower.layers.29.self_attn.q_proj",
+      "thinker.audio_tower.layers.29.self_attn.out_proj",
+      "thinker.audio_tower.layers.29.fc1",
+      "thinker.audio_tower.layers.29.fc2",
+      "thinker.audio_tower.layers.30.self_attn.k_proj",
+      "thinker.audio_tower.layers.30.self_attn.v_proj",
+      "thinker.audio_tower.layers.30.self_attn.q_proj",
+      "thinker.audio_tower.layers.30.self_attn.out_proj",
+      "thinker.audio_tower.layers.30.fc1",
+      "thinker.audio_tower.layers.30.fc2",
+      "thinker.audio_tower.layers.31.self_attn.k_proj",
+      "thinker.audio_tower.layers.31.self_attn.v_proj",
+      "thinker.audio_tower.layers.31.self_attn.q_proj",
+      "thinker.audio_tower.layers.31.self_attn.out_proj",
+      "thinker.audio_tower.layers.31.fc1",
+      "thinker.audio_tower.layers.31.fc2",
+      "thinker.audio_tower.conv_out",
+      "thinker.audio_tower.proj1",
+      "thinker.audio_tower.proj2",
+      "thinker.visual.merger_list.0.mlp.0",
+      "thinker.visual.merger_list.0.mlp.2",
+      "thinker.visual.merger_list.1.mlp.0",
+      "thinker.visual.merger_list.1.mlp.2",
+      "thinker.visual.merger_list.2.mlp.0",
+      "thinker.visual.merger_list.2.mlp.2",
+      "thinker.visual.blocks.0.attn.qkv",
+      "thinker.visual.blocks.0.attn.proj",
+      "thinker.visual.blocks.0.mlp.linear_fc1",
+      "thinker.visual.blocks.0.mlp.linear_fc2",
+      "thinker.visual.blocks.1.attn.qkv",
+      "thinker.visual.blocks.1.attn.proj",
+      "thinker.visual.blocks.1.mlp.linear_fc1",
+      "thinker.visual.blocks.1.mlp.linear_fc2",
+      "thinker.visual.blocks.2.attn.qkv",
+      "thinker.visual.blocks.2.attn.proj",
+      "thinker.visual.blocks.2.mlp.linear_fc1",
+      "thinker.visual.blocks.2.mlp.linear_fc2",
+      "thinker.visual.blocks.3.attn.qkv",
+      "thinker.visual.blocks.3.attn.proj",
+      "thinker.visual.blocks.3.mlp.linear_fc1",
+      "thinker.visual.blocks.3.mlp.linear_fc2",
+      "thinker.visual.blocks.4.attn.qkv",
+      "thinker.visual.blocks.4.attn.proj",
+      "thinker.visual.blocks.4.mlp.linear_fc1",
+      "thinker.visual.blocks.4.mlp.linear_fc2",
+      "thinker.visual.blocks.5.attn.qkv",
+      "thinker.visual.blocks.5.attn.proj",
+      "thinker.visual.blocks.5.mlp.linear_fc1",
+      "thinker.visual.blocks.5.mlp.linear_fc2",
+      "thinker.visual.blocks.6.attn.qkv",
+      "thinker.visual.blocks.6.attn.proj",
+      "thinker.visual.blocks.6.mlp.linear_fc1",
+      "thinker.visual.blocks.6.mlp.linear_fc2",
+      "thinker.visual.blocks.7.attn.qkv",
+      "thinker.visual.blocks.7.attn.proj",
+      "thinker.visual.blocks.7.mlp.linear_fc1",
+      "thinker.visual.blocks.7.mlp.linear_fc2",
+      "thinker.visual.blocks.8.attn.qkv",
+      "thinker.visual.blocks.8.attn.proj",
+      "thinker.visual.blocks.8.mlp.linear_fc1",
+      "thinker.visual.blocks.8.mlp.linear_fc2",
+      "thinker.visual.blocks.9.attn.qkv",
+      "thinker.visual.blocks.9.attn.proj",
+      "thinker.visual.blocks.9.mlp.linear_fc1",
+      "thinker.visual.blocks.9.mlp.linear_fc2",
+      "thinker.visual.blocks.10.attn.qkv",
+      "thinker.visual.blocks.10.attn.proj",
+      "thinker.visual.blocks.10.mlp.linear_fc1",
+      "thinker.visual.blocks.10.mlp.linear_fc2",
+      "thinker.visual.blocks.11.attn.qkv",
+      "thinker.visual.blocks.11.attn.proj",
+      "thinker.visual.blocks.11.mlp.linear_fc1",
+      "thinker.visual.blocks.11.mlp.linear_fc2",
+      "thinker.visual.blocks.12.attn.qkv",
+      "thinker.visual.blocks.12.attn.proj",
+      "thinker.visual.blocks.12.mlp.linear_fc1",
+      "thinker.visual.blocks.12.mlp.linear_fc2",
+      "thinker.visual.blocks.13.attn.qkv",
+      "thinker.visual.blocks.13.attn.proj",
+      "thinker.visual.blocks.13.mlp.linear_fc1",
+      "thinker.visual.blocks.13.mlp.linear_fc2",
+      "thinker.visual.blocks.14.attn.qkv",
+      "thinker.visual.blocks.14.attn.proj",
+      "thinker.visual.blocks.14.mlp.linear_fc1",
+      "thinker.visual.blocks.14.mlp.linear_fc2",
+      "thinker.visual.blocks.15.attn.qkv",
+      "thinker.visual.blocks.15.attn.proj",
+      "thinker.visual.blocks.15.mlp.linear_fc1",
+      "thinker.visual.blocks.15.mlp.linear_fc2",
+      "thinker.visual.blocks.16.attn.qkv",
+      "thinker.visual.blocks.16.attn.proj",
+      "thinker.visual.blocks.16.mlp.linear_fc1",
+      "thinker.visual.blocks.16.mlp.linear_fc2",
+      "thinker.visual.blocks.17.attn.qkv",
+      "thinker.visual.blocks.17.attn.proj",
+      "thinker.visual.blocks.17.mlp.linear_fc1",
+      "thinker.visual.blocks.17.mlp.linear_fc2",
+      "thinker.visual.blocks.18.attn.qkv",
+      "thinker.visual.blocks.18.attn.proj",
+      "thinker.visual.blocks.18.mlp.linear_fc1",
+      "thinker.visual.blocks.18.mlp.linear_fc2",
+      "thinker.visual.blocks.19.attn.qkv",
+      "thinker.visual.blocks.19.attn.proj",
+      "thinker.visual.blocks.19.mlp.linear_fc1",
+      "thinker.visual.blocks.19.mlp.linear_fc2",
+      "thinker.visual.blocks.20.attn.qkv",
+      "thinker.visual.blocks.20.attn.proj",
+      "thinker.visual.blocks.20.mlp.linear_fc1",
+      "thinker.visual.blocks.20.mlp.linear_fc2",
+      "thinker.visual.blocks.21.attn.qkv",
+      "thinker.visual.blocks.21.attn.proj",
+      "thinker.visual.blocks.21.mlp.linear_fc1",
+      "thinker.visual.blocks.21.mlp.linear_fc2",
+      "thinker.visual.blocks.22.attn.qkv",
+      "thinker.visual.blocks.22.attn.proj",
+      "thinker.visual.blocks.22.mlp.linear_fc1",
+      "thinker.visual.blocks.22.mlp.linear_fc2",
+      "thinker.visual.blocks.23.attn.qkv",
+      "thinker.visual.blocks.23.attn.proj",
+      "thinker.visual.blocks.23.mlp.linear_fc1",
+      "thinker.visual.blocks.23.mlp.linear_fc2",
+      "thinker.visual.blocks.24.attn.qkv",
+      "thinker.visual.blocks.24.attn.proj",
+      "thinker.visual.blocks.24.mlp.linear_fc1",
+      "thinker.visual.blocks.24.mlp.linear_fc2",
+      "thinker.visual.blocks.25.attn.qkv",
+      "thinker.visual.blocks.25.attn.proj",
+      "thinker.visual.blocks.25.mlp.linear_fc1",
+      "thinker.visual.blocks.25.mlp.linear_fc2",
+      "thinker.visual.blocks.26.attn.qkv",
+      "thinker.visual.blocks.26.attn.proj",
+      "thinker.visual.blocks.26.mlp.linear_fc1",
+      "thinker.visual.blocks.26.mlp.linear_fc2",
+      "thinker.visual.merger.mlp.0",
+      "thinker.visual.merger.mlp.2",
+      "thinker.model.layers.0.mlp.gate",
+      "thinker.model.layers.1.mlp.gate",
+      "thinker.model.layers.2.mlp.gate",
+      "thinker.model.layers.3.mlp.gate",
+      "thinker.model.layers.4.mlp.gate",
+      "thinker.model.layers.5.mlp.gate",
+      "thinker.model.layers.6.mlp.gate",
+      "thinker.model.layers.7.mlp.gate",
+      "thinker.model.layers.8.mlp.gate",
+      "thinker.model.layers.9.mlp.gate",
+      "thinker.model.layers.10.mlp.gate",
+      "thinker.model.layers.11.mlp.gate",
+      "thinker.model.layers.12.mlp.gate",
+      "thinker.model.layers.13.mlp.gate",
+      "thinker.model.layers.14.mlp.gate",
+      "thinker.model.layers.15.mlp.gate",
+      "thinker.model.layers.16.mlp.gate",
+      "thinker.model.layers.17.mlp.gate",
+      "thinker.model.layers.18.mlp.gate",
+      "thinker.model.layers.19.mlp.gate",
+      "thinker.model.layers.20.mlp.gate",
+      "thinker.model.layers.21.mlp.gate",
+      "thinker.model.layers.22.mlp.gate",
+      "thinker.model.layers.23.mlp.gate",
+      "thinker.model.layers.24.mlp.gate",
+      "thinker.model.layers.25.mlp.gate",
+      "thinker.model.layers.26.mlp.gate",
+      "thinker.model.layers.27.mlp.gate",
+      "thinker.model.layers.28.mlp.gate",
+      "thinker.model.layers.29.mlp.gate",
+      "thinker.model.layers.30.mlp.gate",
+      "thinker.model.layers.31.mlp.gate",
+      "thinker.model.layers.32.mlp.gate",
+      "thinker.model.layers.33.mlp.gate",
+      "thinker.model.layers.34.mlp.gate",
+      "thinker.model.layers.35.mlp.gate",
+      "thinker.model.layers.36.mlp.gate",
+      "thinker.model.layers.37.mlp.gate",
+      "thinker.model.layers.38.mlp.gate",
+      "thinker.model.layers.39.mlp.gate",
+      "thinker.model.layers.40.mlp.gate",
+      "thinker.model.layers.41.mlp.gate",
+      "thinker.model.layers.42.mlp.gate",
+      "thinker.model.layers.43.mlp.gate",
+      "thinker.model.layers.44.mlp.gate",
+      "thinker.model.layers.45.mlp.gate",
+      "thinker.model.layers.46.mlp.gate",
+      "thinker.model.layers.47.mlp.gate",
+      "thinker.lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.11.0"
+  },
+  "transformers_version": "4.57.0.dev0",
+  "tts_bos_token_id": 151672,
+  "tts_eos_token_id": 151673,
+  "tts_pad_token_id": 151671,
+  "user_token_id": 872
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "max_new_tokens": 32768,
+  "repetition_penalty": 1.0,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40b8dca1d63858cacab6d8b4750e7586f2adde06f0415ee8d7ebc46e6b0c59d
+size 5000651392

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d80f45951ffe31d9a7790243d8fb21d2fdbdf4531d25e23ece55f3603701595
+size 5001406576

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d65074b354032338f041d52b4ab107142b8e7b7c9f6b9849d3444e4c2034a0
+size 5001941584

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b650ab7cc72508f466e23faeb2ecbc97834cf36896f8a24c735ca8e077f88db1
+size 4842354408

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa646c77d3a76d216d7f7cd6d7c75a81754d661fe22ec7551d97e288e0eaca3
+size 622854280

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 16,
+  "processor_class": "Qwen3OmniMoeProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<|image_pad|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09267689b8362020b9763b65dd5be7e086b31e28d72e02837a9e781de9a91bc7
+size 11423986

tokenizer_config.json

@@ -0,0 +1,317 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "image_token": "<|image_pad|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3OmniMoeProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,54 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "fps": null,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "num_frames": null,
+  "pad_size": null,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 16,
+  "processor_class": "Qwen3OmniMoeProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_metadata": false,
+  "sampling_rate": 16000,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}