Model upload

Co-authored-by: Bo-Kyeong Kim <bokyeong.kim@nota.ai>

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+*.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3.5-4B
+base_model_relation: quantized
+pipeline_tag: text-generation
+tags:
+- qwen3.5
+- quantization
+- int4
+- w4a16
+- compressed-tensors
+- quantization-aware-distillation
+- efficient-inference
+---
+
+<!-- TODO(release): fill the arXiv id. -->
+
+<h1 align="center">Qwen3.5-4B-QAD-W4A16</h1>
+
+<div align="center">
+
+[![paper](https://img.shields.io/badge/arXiv-2607.04244-b31b1b.svg)](https://arxiv.org/abs/2607.04244)
+[![code](https://img.shields.io/badge/GitHub-full%20pipeline-181717?logo=github)](https://github.com/nota-github/adaptfm-quant-dflash)
+<br/>
+[![target model](https://img.shields.io/badge/%F0%9F%A4%97%20Target-Qwen3.5--4B--QAD--W4A16-yellow)](https://huggingface.co/nota-ai/Qwen3.5-4B-QAD-W4A16)
+[![drafter model](https://img.shields.io/badge/%F0%9F%A4%97%20Drafter-Qwen3.5--4B--DFlash--GPTQ--W4A16-yellow)](https://huggingface.co/nota-ai/Qwen3.5-4B-DFlash-GPTQ-W4A16)
+
+</div>
+
+## Introduction
+
+<p align="center">
+  <img src="figure/pipeline.png" alt="Pipeline: QAD INT4 target distillation, two-stage block-diffusion DFlash drafter training, and INT4-GPTQ + SWA drafter optimization."  width="800">
+</p>
+
+We reduce Qwen3.5-4B inference latency on a single A10G by quantizing both the target model and its speculative-decoding drafter to INT4, while maintaining quality across all three gates (MMLU-Pro, IFEval, GPQA-Diamond). This repository reproduces our 3rd-place Efficient Qwen Competition ([AdaptFM @ ICML 2026](https://adaptfm.gitlab.io/)) entry end to end. It combines three techniques:
+
+- **Quantization-Aware Distillation (QAD):** trains the INT4 target model to follow the original BF16 model's distribution, recovering the accuracy that post-training quantization (PTQ) loses.
+- **Two-Stage Training for Block-Diffusion Drafter:** pretrains the DFlash drafter with the BF16 target, then finetunes it on the QAD-applied INT4 target so it aligns with the quantized target distribution better than direct QAD-target training does.
+- **Drafter Optimization:** applies INT4 GPTQ and Sliding-Window Attention (SWA) to reduce drafter overhead while maintaining acceptance length.
+
+**Hardware:** Final serving and evaluation run on a single NVIDIA A10G 24 GB GPU. Retraining the QAD target and drafter requires an 80 GB-class multi-GPU machine, with at least 2 GPUs and preferably 8 GPUs. The gated prompt dataset is a one-time ~42 GB download.
+
+## Quickstart (vLLM)
+
+```bash
+vllm serve nota-ai/Qwen3.5-4B-QAD-W4A16 \
+    --quantization compressed-tensors \
+    --trust-remote-code
+```
+
+- For speculative decoding with the companion W4A16 DFlash drafter, see the **[drafter card](https://huggingface.co/nota-ai/Qwen3.5-4B-DFlash-GPTQ-W4A16)**.
+
+## Citation
+
+```bibtex
+@article{kim2026quantize,
+  title   = {Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B},
+  author  = {Jaeyeon Kim and Jewon Lee and Bo-Kyeong Kim},
+  journal = {arXiv preprint arXiv:2607.04244},
+  year    = {2026}
+}
+```
+
+
+## License & provenance
+
+Apache-2.0, derived from [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)
+(Apache-2.0) with INT4 initialization from
+[cyankiwi/Qwen3.5-4B-AWQ-4bit](https://huggingface.co/cyankiwi/Qwen3.5-4B-AWQ-4bit).
+Distillation data derives from NVIDIA's [Nemotron-Post-Training-Dataset-v2](https://huggingface.co/datasets/nvidia/Nemotron-Post-Training-Dataset-v2) (gated;
+see its terms).

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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- 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 +1,384 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "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_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "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": true,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "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": "minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.language_model.layers.0.linear_attn.conv1d",
+      "model.language_model.layers.0.linear_attn.in_proj_a",
+      "model.language_model.layers.0.linear_attn.in_proj_b",
+      "model.language_model.layers.1.linear_attn.conv1d",
+      "model.language_model.layers.1.linear_attn.in_proj_a",
+      "model.language_model.layers.1.linear_attn.in_proj_b",
+      "model.language_model.layers.10.linear_attn.conv1d",
+      "model.language_model.layers.10.linear_attn.in_proj_a",
+      "model.language_model.layers.10.linear_attn.in_proj_b",
+      "model.language_model.layers.12.linear_attn.conv1d",
+      "model.language_model.layers.12.linear_attn.in_proj_a",
+      "model.language_model.layers.12.linear_attn.in_proj_b",
+      "model.language_model.layers.13.linear_attn.conv1d",
+      "model.language_model.layers.13.linear_attn.in_proj_a",
+      "model.language_model.layers.13.linear_attn.in_proj_b",
+      "model.language_model.layers.14.linear_attn.conv1d",
+      "model.language_model.layers.14.linear_attn.in_proj_a",
+      "model.language_model.layers.14.linear_attn.in_proj_b",
+      "model.language_model.layers.16.linear_attn.conv1d",
+      "model.language_model.layers.16.linear_attn.in_proj_a",
+      "model.language_model.layers.16.linear_attn.in_proj_b",
+      "model.language_model.layers.17.linear_attn.conv1d",
+      "model.language_model.layers.17.linear_attn.in_proj_a",
+      "model.language_model.layers.17.linear_attn.in_proj_b",
+      "model.language_model.layers.18.linear_attn.conv1d",
+      "model.language_model.layers.18.linear_attn.in_proj_a",
+      "model.language_model.layers.18.linear_attn.in_proj_b",
+      "model.language_model.layers.2.linear_attn.conv1d",
+      "model.language_model.layers.2.linear_attn.in_proj_a",
+      "model.language_model.layers.2.linear_attn.in_proj_b",
+      "model.language_model.layers.20.linear_attn.conv1d",
+      "model.language_model.layers.20.linear_attn.in_proj_a",
+      "model.language_model.layers.20.linear_attn.in_proj_b",
+      "model.language_model.layers.21.linear_attn.conv1d",
+      "model.language_model.layers.21.linear_attn.in_proj_a",
+      "model.language_model.layers.21.linear_attn.in_proj_b",
+      "model.language_model.layers.22.linear_attn.conv1d",
+      "model.language_model.layers.22.linear_attn.in_proj_a",
+      "model.language_model.layers.22.linear_attn.in_proj_b",
+      "model.language_model.layers.24.linear_attn.conv1d",
+      "model.language_model.layers.24.linear_attn.in_proj_a",
+      "model.language_model.layers.24.linear_attn.in_proj_b",
+      "model.language_model.layers.25.linear_attn.conv1d",
+      "model.language_model.layers.25.linear_attn.in_proj_a",
+      "model.language_model.layers.25.linear_attn.in_proj_b",
+      "model.language_model.layers.26.linear_attn.conv1d",
+      "model.language_model.layers.26.linear_attn.in_proj_a",
+      "model.language_model.layers.26.linear_attn.in_proj_b",
+      "model.language_model.layers.28.linear_attn.conv1d",
+      "model.language_model.layers.28.linear_attn.in_proj_a",
+      "model.language_model.layers.28.linear_attn.in_proj_b",
+      "model.language_model.layers.29.linear_attn.conv1d",
+      "model.language_model.layers.29.linear_attn.in_proj_a",
+      "model.language_model.layers.29.linear_attn.in_proj_b",
+      "model.language_model.layers.30.linear_attn.conv1d",
+      "model.language_model.layers.30.linear_attn.in_proj_a",
+      "model.language_model.layers.30.linear_attn.in_proj_b",
+      "model.language_model.layers.4.linear_attn.conv1d",
+      "model.language_model.layers.4.linear_attn.in_proj_a",
+      "model.language_model.layers.4.linear_attn.in_proj_b",
+      "model.language_model.layers.5.linear_attn.conv1d",
+      "model.language_model.layers.5.linear_attn.in_proj_a",
+      "model.language_model.layers.5.linear_attn.in_proj_b",
+      "model.language_model.layers.6.linear_attn.conv1d",
+      "model.language_model.layers.6.linear_attn.in_proj_a",
+      "model.language_model.layers.6.linear_attn.in_proj_b",
+      "model.language_model.layers.8.linear_attn.conv1d",
+      "model.language_model.layers.8.linear_attn.in_proj_a",
+      "model.language_model.layers.8.linear_attn.in_proj_b",
+      "model.language_model.layers.9.linear_attn.conv1d",
+      "model.language_model.layers.9.linear_attn.in_proj_a",
+      "model.language_model.layers.9.linear_attn.in_proj_b",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.0.norm1",
+      "model.visual.blocks.0.norm2",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.1.norm1",
+      "model.visual.blocks.1.norm2",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.10.norm1",
+      "model.visual.blocks.10.norm2",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.11.norm1",
+      "model.visual.blocks.11.norm2",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.12.norm1",
+      "model.visual.blocks.12.norm2",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.13.norm1",
+      "model.visual.blocks.13.norm2",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.14.norm1",
+      "model.visual.blocks.14.norm2",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.15.norm1",
+      "model.visual.blocks.15.norm2",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.16.norm1",
+      "model.visual.blocks.16.norm2",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.17.norm1",
+      "model.visual.blocks.17.norm2",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.18.norm1",
+      "model.visual.blocks.18.norm2",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.19.norm1",
+      "model.visual.blocks.19.norm2",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.2.norm1",
+      "model.visual.blocks.2.norm2",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.20.norm1",
+      "model.visual.blocks.20.norm2",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.21.norm1",
+      "model.visual.blocks.21.norm2",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.22.norm1",
+      "model.visual.blocks.22.norm2",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.23.norm1",
+      "model.visual.blocks.23.norm2",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.3.norm1",
+      "model.visual.blocks.3.norm2",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.4.norm1",
+      "model.visual.blocks.4.norm2",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.5.norm1",
+      "model.visual.blocks.5.norm2",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.6.norm1",
+      "model.visual.blocks.6.norm2",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.7.norm1",
+      "model.visual.blocks.7.norm2",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.8.norm1",
+      "model.visual.blocks.8.norm2",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.9.norm1",
+      "model.visual.blocks.9.norm2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.merger.norm",
+      "model.visual.patch_embed.proj",
+      "model.visual.pos_embed",
+      "mtp.fc",
+      "mtp.layers.0.input_layernorm",
+      "mtp.layers.0.mlp.down_proj",
+      "mtp.layers.0.mlp.gate_proj",
+      "mtp.layers.0.mlp.up_proj",
+      "mtp.layers.0.post_attention_layernorm",
+      "mtp.layers.0.self_attn.k_norm",
+      "mtp.layers.0.self_attn.k_proj",
+      "mtp.layers.0.self_attn.o_proj",
+      "mtp.layers.0.self_attn.q_norm",
+      "mtp.layers.0.self_attn.q_proj",
+      "mtp.layers.0.self_attn.v_proj",
+      "mtp.norm",
+      "mtp.pre_fc_norm_embedding",
+      "mtp.pre_fc_norm_hidden"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.14.1"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df3baab330b306ca44461a156234b321bea78496723ec6d1d70e60b7c652f24
+size 4194960928

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

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"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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": 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": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}