Add Qwen3.6-27B-NVFP4: NVFP4 quantized with llm-compressor (BF16 vision + DeltaNet preserved)

.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 +1,232 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
+pipeline_tag: image-text-to-text
+base_model: Qwen/Qwen3.6-27B
+tags:
+  - nvfp4
+  - quantized
+  - compressed-tensors
+  - blackwell
+  - qwen3.6
+  - vlm
+  - vllm
+quantized_by: vrfai
+---
+
+# Qwen3.6-27B-NVFP4
+
+NVFP4 quantized version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) by [vrfai](https://huggingface.co/vrfai) using [llm-compressor](https://github.com/vllm-project/llm-compressor).
+
+Tested and deployed on **2× NVIDIA RTX 5090** with full tensor-parallel inference via vLLM.
+
+## NVFP4 Quantization Details
+
+| | |
+|---|---|
+| **Base model** | [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) |
+| **Quantization** | NVFP4 — weights FP4, activations FP4 (dynamic local), scales FP8 |
+| **Format** | `compressed-tensors` (native vLLM support) |
+| **Tool** | [vllm-project/llm-compressor](https://github.com/vllm-project/llm-compressor) |
+| **Requires** | NVIDIA Blackwell GPU (SM 120+), vLLM ≥ 0.19 |
+
+### What's Quantized / What's Not
+
+The quantization strategy carefully preserves the most sensitive components in BF16 while aggressively compressing the compute-heavy stable layers:
+
+| Component | Precision | Reason |
+|---|---|---|
+| FFN / MLP — all 64 transformer layers | **NVFP4** | High parameter density, stable under quantization |
+| Full-attention projections (q/k/v/o) — 16 GQA layers | **NVFP4** | Standard attention, tolerant to 4-bit |
+| DeltaNet / Linear-attention projections — 48 layers | **BF16** | Gated linear recurrence is sensitive to numerical errors |
+| Vision encoder — all 27 blocks + merger | **BF16** | Vision tower preserved to maintain multimodal quality |
+| `lm_head` | **BF16** | Output logits preserved for generation stability |
+
+> The architecture of Qwen3.6-27B interleaves 3 × DeltaNet (linear attention) layers with 1 × full GQA attention every 4 layers (16 such groups × 4 = 64 layers total). Only the full-attention group and all FFN layers are quantized; the DeltaNet recurrent cores are untouched.
+
+### Quantization Config (llm-compressor)
+
+```yaml
+# recipe.yaml
+QuantizationModifier:
+  targets: [Linear]
+  scheme: NVFP4
+  ignore:
+    - lm_head
+    # Vision encoder — all 27 blocks (attn + mlp) + merger
+    - re:model\.visual\.blocks\.\d+\..*
+    - model.visual.merger.linear_fc1
+    - model.visual.merger.linear_fc2
+    # DeltaNet / Linear-attention layers (layers 0–2, 4–6, 8–10, ..., 60–62)
+    - re:model\.language_model\.layers\.\d+\.linear_attn\..*
+```
+
+---
+
+## Quick Start (vLLM)
+
+```bash
+vllm serve vrfai/Qwen3.6-27B-NVFP4 \
+  --max-model-len 8192 \
+  --gpu-memory-utilization 0.9 \
+  --dtype auto \
+  --trust-remote-code \
+  --tensor-parallel-size 2
+```
+
+For single-GPU Blackwell (e.g., RTX 5090 with 32 GB):
+
+```bash
+vllm serve vrfai/Qwen3.6-27B-NVFP4 \
+  --max-model-len 8192 \
+  --gpu-memory-utilization 0.92 \
+  --dtype auto \
+  --trust-remote-code
+```
+
+### Python (Transformers)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "vrfai/Qwen3.6-27B-NVFP4"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+messages = [{"role": "user", "content": "Explain quantization in one paragraph."}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
+```
+
+### OpenAI-compatible API
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+
+response = client.chat.completions.create(
+    model="vrfai/Qwen3.6-27B-NVFP4",
+    messages=[{"role": "user", "content": "Hello!"}],
+    temperature=0.7,
+    max_tokens=512,
+)
+print(response.choices[0].message.content)
+```
+
+---
+
+## Tested Environment
+
+| Component | Version |
+|-----------|---------|
+| vLLM | 0.19.1 |
+| Transformers | 5.6.0 |
+| PyTorch | 2.10.0+cu128 |
+| CUDA | 12.8 (nvcc 12.8.61) |
+| llm-compressor | compressed-tensors 0.14.0.1 |
+| GPU | 2× NVIDIA RTX 5090 (tensor-parallel-size 2) |
+| OS | Ubuntu 24 |
+
+---
+
+## Best Practices
+
+**Sampling parameters:**
+
+| Mode | temperature | top_p | top_k | presence_penalty |
+|------|-------------|-------|-------|------------------|
+| Thinking — general | 1.0 | 0.95 | 20 | 0.0 |
+| Thinking — coding (WebDev) | 0.6 | 0.95 | 20 | 0.0 |
+| Non-thinking / instruct | 0.7 | 0.80 | 20 | 1.5 |
+
+**Output length:** Recommend `max_new_tokens=32768` for most tasks; up to 81920 for complex math/coding benchmarks.
+
+**Thinking mode** (enable via chat template):
+```python
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    chat_template_kwargs={"enable_thinking": True},
+)
+```
+
+---
+
+## Credits
+
+- **Original model:** [Qwen Team](https://huggingface.co/Qwen) (Alibaba Group)
+- **NVFP4 quantization:** [vrfai](https://huggingface.co/vrfai)
+- **Quantization framework:** [vllm-project/llm-compressor](https://github.com/vllm-project/llm-compressor)
+
+---
+
+*Below is the original model card from [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B):*
+
+---
+
+<img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.6/logo.png">
+
+[![Qwen Chat](https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5)](https://chat.qwen.ai)
+
+> [!Note]
+> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
+>
+> These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
+
+Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
+
+## Qwen3.6 Highlights
+
+This release delivers substantial upgrades, particularly in
+
+- **Agentic Coding:** the model now handles frontend workflows and repository-level reasoning with greater fluency and precision.
+- **Thinking Preservation:** we've introduced a new option to retain reasoning context from historical messages, streamlining iterative development and reducing overhead.
+
+![Benchmark Results](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3.6/Figures/qwen3.6_27b_score.png)
+
+For more details, please refer to our blog post [Qwen3.6-27B](https://qwen.ai/blog?id=qwen3.6-27b).
+
+## Model Overview
+
+- Type: Causal Language Model with Vision Encoder
+- Training Stage: Pre-training & Post-training
+- Language Model
+    - Number of Parameters: 27B
+    - Hidden Dimension: 5120
+    - Token Embedding: 248320 (Padded)
+    - Number of Layers: 64
+    - Hidden Layout: 16 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
+    - Gated DeltaNet:
+        - Number of Linear Attention Heads: 48 for V and 16 for QK
+        - Head Dimension: 128
+    - Gated Attention:
+        - Number of Attention Heads: 24 for Q and 4 for KV
+        - Head Dimension: 256
+        - Rotary Position Embedding Dimension: 64
+    - Feed Forward Network:
+        - Intermediate Dimension: 17408
+    - LM Output: 248320 (Padded)
+    - MTP: trained with multi-steps
+- Context Length: 262,144 natively and extensible up to 1,010,000 tokens.
+
+### Citation
+
+```bibtex
+@misc{qwen3.6-27b,
+    title  = {{Qwen3.6-27B}: Flagship-Level Coding in a {27B} Dense Model},
+    author = {{Qwen Team}},
+    month  = {April},
+    year   = {2026},
+    url    = {https://qwen.ai/blog?id=qwen3.6-27b}
+}
+```

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- 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" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|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 %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,542 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "nvfp4-pack-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.language_model.layers.0.linear_attn.out_proj",
+      "model.language_model.layers.0.linear_attn.in_proj_qkv",
+      "model.language_model.layers.0.linear_attn.in_proj_z",
+      "model.language_model.layers.0.linear_attn.in_proj_b",
+      "model.language_model.layers.0.linear_attn.in_proj_a",
+      "model.language_model.layers.1.linear_attn.out_proj",
+      "model.language_model.layers.1.linear_attn.in_proj_qkv",
+      "model.language_model.layers.1.linear_attn.in_proj_z",
+      "model.language_model.layers.1.linear_attn.in_proj_b",
+      "model.language_model.layers.1.linear_attn.in_proj_a",
+      "model.language_model.layers.2.linear_attn.out_proj",
+      "model.language_model.layers.2.linear_attn.in_proj_qkv",
+      "model.language_model.layers.2.linear_attn.in_proj_z",
+      "model.language_model.layers.2.linear_attn.in_proj_b",
+      "model.language_model.layers.2.linear_attn.in_proj_a",
+      "model.language_model.layers.4.linear_attn.out_proj",
+      "model.language_model.layers.4.linear_attn.in_proj_qkv",
+      "model.language_model.layers.4.linear_attn.in_proj_z",
+      "model.language_model.layers.4.linear_attn.in_proj_b",
+      "model.language_model.layers.4.linear_attn.in_proj_a",
+      "model.language_model.layers.5.linear_attn.out_proj",
+      "model.language_model.layers.5.linear_attn.in_proj_qkv",
+      "model.language_model.layers.5.linear_attn.in_proj_z",
+      "model.language_model.layers.5.linear_attn.in_proj_b",
+      "model.language_model.layers.5.linear_attn.in_proj_a",
+      "model.language_model.layers.6.linear_attn.out_proj",
+      "model.language_model.layers.6.linear_attn.in_proj_qkv",
+      "model.language_model.layers.6.linear_attn.in_proj_z",
+      "model.language_model.layers.6.linear_attn.in_proj_b",
+      "model.language_model.layers.6.linear_attn.in_proj_a",
+      "model.language_model.layers.8.linear_attn.out_proj",
+      "model.language_model.layers.8.linear_attn.in_proj_qkv",
+      "model.language_model.layers.8.linear_attn.in_proj_z",
+      "model.language_model.layers.8.linear_attn.in_proj_b",
+      "model.language_model.layers.8.linear_attn.in_proj_a",
+      "model.language_model.layers.9.linear_attn.out_proj",
+      "model.language_model.layers.9.linear_attn.in_proj_qkv",
+      "model.language_model.layers.9.linear_attn.in_proj_z",
+      "model.language_model.layers.9.linear_attn.in_proj_b",
+      "model.language_model.layers.9.linear_attn.in_proj_a",
+      "model.language_model.layers.10.linear_attn.out_proj",
+      "model.language_model.layers.10.linear_attn.in_proj_qkv",
+      "model.language_model.layers.10.linear_attn.in_proj_z",
+      "model.language_model.layers.10.linear_attn.in_proj_b",
+      "model.language_model.layers.10.linear_attn.in_proj_a",
+      "model.language_model.layers.12.linear_attn.out_proj",
+      "model.language_model.layers.12.linear_attn.in_proj_qkv",
+      "model.language_model.layers.12.linear_attn.in_proj_z",
+      "model.language_model.layers.12.linear_attn.in_proj_b",
+      "model.language_model.layers.12.linear_attn.in_proj_a",
+      "model.language_model.layers.13.linear_attn.out_proj",
+      "model.language_model.layers.13.linear_attn.in_proj_qkv",
+      "model.language_model.layers.13.linear_attn.in_proj_z",
+      "model.language_model.layers.13.linear_attn.in_proj_b",
+      "model.language_model.layers.13.linear_attn.in_proj_a",
+      "model.language_model.layers.14.linear_attn.out_proj",
+      "model.language_model.layers.14.linear_attn.in_proj_qkv",
+      "model.language_model.layers.14.linear_attn.in_proj_z",
+      "model.language_model.layers.14.linear_attn.in_proj_b",
+      "model.language_model.layers.14.linear_attn.in_proj_a",
+      "model.language_model.layers.16.linear_attn.out_proj",
+      "model.language_model.layers.16.linear_attn.in_proj_qkv",
+      "model.language_model.layers.16.linear_attn.in_proj_z",
+      "model.language_model.layers.16.linear_attn.in_proj_b",
+      "model.language_model.layers.16.linear_attn.in_proj_a",
+      "model.language_model.layers.17.linear_attn.out_proj",
+      "model.language_model.layers.17.linear_attn.in_proj_qkv",
+      "model.language_model.layers.17.linear_attn.in_proj_z",
+      "model.language_model.layers.17.linear_attn.in_proj_b",
+      "model.language_model.layers.17.linear_attn.in_proj_a",
+      "model.language_model.layers.18.linear_attn.out_proj",
+      "model.language_model.layers.18.linear_attn.in_proj_qkv",
+      "model.language_model.layers.18.linear_attn.in_proj_z",
+      "model.language_model.layers.18.linear_attn.in_proj_b",
+      "model.language_model.layers.18.linear_attn.in_proj_a",
+      "model.language_model.layers.20.linear_attn.out_proj",
+      "model.language_model.layers.20.linear_attn.in_proj_qkv",
+      "model.language_model.layers.20.linear_attn.in_proj_z",
+      "model.language_model.layers.20.linear_attn.in_proj_b",
+      "model.language_model.layers.20.linear_attn.in_proj_a",
+      "model.language_model.layers.21.linear_attn.out_proj",
+      "model.language_model.layers.21.linear_attn.in_proj_qkv",
+      "model.language_model.layers.21.linear_attn.in_proj_z",
+      "model.language_model.layers.21.linear_attn.in_proj_b",
+      "model.language_model.layers.21.linear_attn.in_proj_a",
+      "model.language_model.layers.22.linear_attn.out_proj",
+      "model.language_model.layers.22.linear_attn.in_proj_qkv",
+      "model.language_model.layers.22.linear_attn.in_proj_z",
+      "model.language_model.layers.22.linear_attn.in_proj_b",
+      "model.language_model.layers.22.linear_attn.in_proj_a",
+      "model.language_model.layers.24.linear_attn.out_proj",
+      "model.language_model.layers.24.linear_attn.in_proj_qkv",
+      "model.language_model.layers.24.linear_attn.in_proj_z",
+      "model.language_model.layers.24.linear_attn.in_proj_b",
+      "model.language_model.layers.24.linear_attn.in_proj_a",
+      "model.language_model.layers.25.linear_attn.out_proj",
+      "model.language_model.layers.25.linear_attn.in_proj_qkv",
+      "model.language_model.layers.25.linear_attn.in_proj_z",
+      "model.language_model.layers.25.linear_attn.in_proj_b",
+      "model.language_model.layers.25.linear_attn.in_proj_a",
+      "model.language_model.layers.26.linear_attn.out_proj",
+      "model.language_model.layers.26.linear_attn.in_proj_qkv",
+      "model.language_model.layers.26.linear_attn.in_proj_z",
+      "model.language_model.layers.26.linear_attn.in_proj_b",
+      "model.language_model.layers.26.linear_attn.in_proj_a",
+      "model.language_model.layers.28.linear_attn.out_proj",
+      "model.language_model.layers.28.linear_attn.in_proj_qkv",
+      "model.language_model.layers.28.linear_attn.in_proj_z",
+      "model.language_model.layers.28.linear_attn.in_proj_b",
+      "model.language_model.layers.28.linear_attn.in_proj_a",
+      "model.language_model.layers.29.linear_attn.out_proj",
+      "model.language_model.layers.29.linear_attn.in_proj_qkv",
+      "model.language_model.layers.29.linear_attn.in_proj_z",
+      "model.language_model.layers.29.linear_attn.in_proj_b",
+      "model.language_model.layers.29.linear_attn.in_proj_a",
+      "model.language_model.layers.30.linear_attn.out_proj",
+      "model.language_model.layers.30.linear_attn.in_proj_qkv",
+      "model.language_model.layers.30.linear_attn.in_proj_z",
+      "model.language_model.layers.30.linear_attn.in_proj_b",
+      "model.language_model.layers.30.linear_attn.in_proj_a",
+      "model.language_model.layers.32.linear_attn.out_proj",
+      "model.language_model.layers.32.linear_attn.in_proj_qkv",
+      "model.language_model.layers.32.linear_attn.in_proj_z",
+      "model.language_model.layers.32.linear_attn.in_proj_b",
+      "model.language_model.layers.32.linear_attn.in_proj_a",
+      "model.language_model.layers.33.linear_attn.out_proj",
+      "model.language_model.layers.33.linear_attn.in_proj_qkv",
+      "model.language_model.layers.33.linear_attn.in_proj_z",
+      "model.language_model.layers.33.linear_attn.in_proj_b",
+      "model.language_model.layers.33.linear_attn.in_proj_a",
+      "model.language_model.layers.34.linear_attn.out_proj",
+      "model.language_model.layers.34.linear_attn.in_proj_qkv",
+      "model.language_model.layers.34.linear_attn.in_proj_z",
+      "model.language_model.layers.34.linear_attn.in_proj_b",
+      "model.language_model.layers.34.linear_attn.in_proj_a",
+      "model.language_model.layers.36.linear_attn.out_proj",
+      "model.language_model.layers.36.linear_attn.in_proj_qkv",
+      "model.language_model.layers.36.linear_attn.in_proj_z",
+      "model.language_model.layers.36.linear_attn.in_proj_b",
+      "model.language_model.layers.36.linear_attn.in_proj_a",
+      "model.language_model.layers.37.linear_attn.out_proj",
+      "model.language_model.layers.37.linear_attn.in_proj_qkv",
+      "model.language_model.layers.37.linear_attn.in_proj_z",
+      "model.language_model.layers.37.linear_attn.in_proj_b",
+      "model.language_model.layers.37.linear_attn.in_proj_a",
+      "model.language_model.layers.38.linear_attn.out_proj",
+      "model.language_model.layers.38.linear_attn.in_proj_qkv",
+      "model.language_model.layers.38.linear_attn.in_proj_z",
+      "model.language_model.layers.38.linear_attn.in_proj_b",
+      "model.language_model.layers.38.linear_attn.in_proj_a",
+      "model.language_model.layers.40.linear_attn.out_proj",
+      "model.language_model.layers.40.linear_attn.in_proj_qkv",
+      "model.language_model.layers.40.linear_attn.in_proj_z",
+      "model.language_model.layers.40.linear_attn.in_proj_b",
+      "model.language_model.layers.40.linear_attn.in_proj_a",
+      "model.language_model.layers.41.linear_attn.out_proj",
+      "model.language_model.layers.41.linear_attn.in_proj_qkv",
+      "model.language_model.layers.41.linear_attn.in_proj_z",
+      "model.language_model.layers.41.linear_attn.in_proj_b",
+      "model.language_model.layers.41.linear_attn.in_proj_a",
+      "model.language_model.layers.42.linear_attn.out_proj",
+      "model.language_model.layers.42.linear_attn.in_proj_qkv",
+      "model.language_model.layers.42.linear_attn.in_proj_z",
+      "model.language_model.layers.42.linear_attn.in_proj_b",
+      "model.language_model.layers.42.linear_attn.in_proj_a",
+      "model.language_model.layers.44.linear_attn.out_proj",
+      "model.language_model.layers.44.linear_attn.in_proj_qkv",
+      "model.language_model.layers.44.linear_attn.in_proj_z",
+      "model.language_model.layers.44.linear_attn.in_proj_b",
+      "model.language_model.layers.44.linear_attn.in_proj_a",
+      "model.language_model.layers.45.linear_attn.out_proj",
+      "model.language_model.layers.45.linear_attn.in_proj_qkv",
+      "model.language_model.layers.45.linear_attn.in_proj_z",
+      "model.language_model.layers.45.linear_attn.in_proj_b",
+      "model.language_model.layers.45.linear_attn.in_proj_a",
+      "model.language_model.layers.46.linear_attn.out_proj",
+      "model.language_model.layers.46.linear_attn.in_proj_qkv",
+      "model.language_model.layers.46.linear_attn.in_proj_z",
+      "model.language_model.layers.46.linear_attn.in_proj_b",
+      "model.language_model.layers.46.linear_attn.in_proj_a",
+      "model.language_model.layers.48.linear_attn.out_proj",
+      "model.language_model.layers.48.linear_attn.in_proj_qkv",
+      "model.language_model.layers.48.linear_attn.in_proj_z",
+      "model.language_model.layers.48.linear_attn.in_proj_b",
+      "model.language_model.layers.48.linear_attn.in_proj_a",
+      "model.language_model.layers.49.linear_attn.out_proj",
+      "model.language_model.layers.49.linear_attn.in_proj_qkv",
+      "model.language_model.layers.49.linear_attn.in_proj_z",
+      "model.language_model.layers.49.linear_attn.in_proj_b",
+      "model.language_model.layers.49.linear_attn.in_proj_a",
+      "model.language_model.layers.50.linear_attn.out_proj",
+      "model.language_model.layers.50.linear_attn.in_proj_qkv",
+      "model.language_model.layers.50.linear_attn.in_proj_z",
+      "model.language_model.layers.50.linear_attn.in_proj_b",
+      "model.language_model.layers.50.linear_attn.in_proj_a",
+      "model.language_model.layers.52.linear_attn.out_proj",
+      "model.language_model.layers.52.linear_attn.in_proj_qkv",
+      "model.language_model.layers.52.linear_attn.in_proj_z",
+      "model.language_model.layers.52.linear_attn.in_proj_b",
+      "model.language_model.layers.52.linear_attn.in_proj_a",
+      "model.language_model.layers.53.linear_attn.out_proj",
+      "model.language_model.layers.53.linear_attn.in_proj_qkv",
+      "model.language_model.layers.53.linear_attn.in_proj_z",
+      "model.language_model.layers.53.linear_attn.in_proj_b",
+      "model.language_model.layers.53.linear_attn.in_proj_a",
+      "model.language_model.layers.54.linear_attn.out_proj",
+      "model.language_model.layers.54.linear_attn.in_proj_qkv",
+      "model.language_model.layers.54.linear_attn.in_proj_z",
+      "model.language_model.layers.54.linear_attn.in_proj_b",
+      "model.language_model.layers.54.linear_attn.in_proj_a",
+      "model.language_model.layers.56.linear_attn.out_proj",
+      "model.language_model.layers.56.linear_attn.in_proj_qkv",
+      "model.language_model.layers.56.linear_attn.in_proj_z",
+      "model.language_model.layers.56.linear_attn.in_proj_b",
+      "model.language_model.layers.56.linear_attn.in_proj_a",
+      "model.language_model.layers.57.linear_attn.out_proj",
+      "model.language_model.layers.57.linear_attn.in_proj_qkv",
+      "model.language_model.layers.57.linear_attn.in_proj_z",
+      "model.language_model.layers.57.linear_attn.in_proj_b",
+      "model.language_model.layers.57.linear_attn.in_proj_a",
+      "model.language_model.layers.58.linear_attn.out_proj",
+      "model.language_model.layers.58.linear_attn.in_proj_qkv",
+      "model.language_model.layers.58.linear_attn.in_proj_z",
+      "model.language_model.layers.58.linear_attn.in_proj_b",
+      "model.language_model.layers.58.linear_attn.in_proj_a",
+      "model.language_model.layers.60.linear_attn.out_proj",
+      "model.language_model.layers.60.linear_attn.in_proj_qkv",
+      "model.language_model.layers.60.linear_attn.in_proj_z",
+      "model.language_model.layers.60.linear_attn.in_proj_b",
+      "model.language_model.layers.60.linear_attn.in_proj_a",
+      "model.language_model.layers.61.linear_attn.out_proj",
+      "model.language_model.layers.61.linear_attn.in_proj_qkv",
+      "model.language_model.layers.61.linear_attn.in_proj_z",
+      "model.language_model.layers.61.linear_attn.in_proj_b",
+      "model.language_model.layers.61.linear_attn.in_proj_a",
+      "model.language_model.layers.62.linear_attn.out_proj",
+      "model.language_model.layers.62.linear_attn.in_proj_qkv",
+      "model.language_model.layers.62.linear_attn.in_proj_z",
+      "model.language_model.layers.62.linear_attn.in_proj_b",
+      "model.language_model.layers.62.linear_attn.in_proj_a",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.14.0.1"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "output_gate_type": "swish",
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49173826a0d6d5962c719662a110259cb2a7e50d23a18c8f9574395693c1be3f
+size 27702391880

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

recipe.yaml

@@ -0,0 +1,8 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: ['re:.*lm_head', 're:.*embed_tokens$', 're:.*visual.*', 're:.*linear_attn.*',
+        're:.*self_attn\.q_norm$', 're:.*self_attn\.k_norm$', 're:.*input_layernorm$', 're:.*post_attention_layernorm$']
+      scheme: NVFP4
+      bypass_divisibility_checks: false

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56427d66f44411c2dec1288b236f6d2c3eeafd611d1d0e2e92ad9301616e1e7
+size 19989424

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}