Duplicate from mlx-community/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX

.gitattributes

@@ -0,0 +1,36 @@
+*.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

README.md

@@ -0,0 +1,149 @@
+---
+license: apache-2.0
+base_model: mlx-community/Qwen3.6-35B-A3B-8bit
+library_name: mlx
+pipeline_tag: text-generation
+language:
+- ko
+- en
+tags:
+- mlx
+- qwen3.6
+- qwen3_5_moe
+- mixture-of-experts
+- reap
+- expert-pruning
+- korean
+- 8-bit
+datasets:
+- eouya2/KGuard-Korean-MoE-Calibration-v1
+---
+
+# Qwen3.6-35B-A3B K-Guard REAP 25% — MLX 8-bit
+
+> Korean model card: [README_ko.md](./README_ko.md)
+
+This is a Korean-oriented, expert-pruned MLX release of
+[`mlx-community/Qwen3.6-35B-A3B-8bit`](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-8bit).
+It applies REAP-style router-weighted expert activation pruning to the routed
+MoE experts while keeping the upstream 8-bit MLX format, top-8 routing, shared
+experts, tokenizer, chat template, and non-MoE components intact.
+
+In this release, **K-Guard** is the name of the Korean-centered calibration
+profile used to collect routing and activation statistics before pruning.
+There is no fine-tuning or weight retraining.
+
+## Model summary
+
+| Property | Value |
+|---|---:|
+| Base checkpoint | `mlx-community/Qwen3.6-35B-A3B-8bit` |
+| Architecture | Qwen3.6 MoE (`qwen3_5_moe`) |
+| MoE layers | 40 |
+| Routed experts per layer | **192**, reduced from 256 |
+| Experts removed per layer | 64 / 256 (**25%**) |
+| Active routed experts per token | 8, unchanged |
+| Shared expert | Preserved |
+| Quantization | MLX affine 8-bit, group size 64 |
+| Local checkpoint size | approximately **27.18 GiB** |
+| Training after pruning | None |
+
+## Calibration and expert selection
+
+Expert importance was observed on a deterministic Korean-centered mixture of
+24,576 sequences:
+
+- 8,192 general Korean instruction and reasoning records
+- 8,192 Korean-English paired records
+- 4,096 general capability replay records
+- 4,096 Qwen3.6 text and reasoning records
+
+The observer covered all 40 MoE layers with a maximum sequence length of 8,192
+tokens and seed 17. For every layer, routed experts were ranked using
+router-weighted activation statistics; the 192 highest-ranked experts were
+retained, the router rows were sliced to the same indices, and top-8 routing
+was preserved.
+
+The calibration file and the complete per-layer/per-expert observation CSV are
+published in
+[`eouya2/KGuard-Korean-MoE-Calibration-v1`](https://huggingface.co/datasets/eouya2/KGuard-Korean-MoE-Calibration-v1).
+
+## Evaluation snapshot
+
+The following scores use the same deterministic evaluation subsets and prompts
+for the base and pruned checkpoints.
+
+| Benchmark | Base 8-bit | This model |
+|---|---:|---:|
+| KMMLU | 66.4 | **60.9** |
+| MMLU-Pro | 64.3 | **58.8** |
+| GSM8K | 96.7 | **96.7** |
+| HumanEval+ pass@1 | 90.9 | **93.3** |
+| Academic 10-benchmark macro | 81.2 | **79.7** |
+
+KMMLU, MMLU-Pro, and GSM8K use 512-item deterministic subsets. HumanEval+
+uses the complete 164-task EvalPlus set. These results are intended for paired
+comparison under the reported local protocols rather than as direct official
+leaderboard submissions.
+
+## Use with MLX
+
+Install MLX LM:
+
+```bash
+pip install -U mlx-lm
+```
+
+Generate from the command line:
+
+```bash
+mlx_lm.generate \
+  --model eouya2/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX \
+  --prompt "한국어로 mixture-of-experts 모델을 간단히 설명해 주세요." \
+  --max-tokens 256 \
+  --temperature 0.0
+```
+
+Or use Python:
+
+```python
+from mlx_lm import generate, load
+
+model_id = "eouya2/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX"
+model, tokenizer = load(model_id)
+
+messages = [{"role": "user", "content": "한국어로 자기소개를 해 주세요."}]
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+
+print(generate(model, tokenizer, prompt=prompt, max_tokens=256))
+```
+
+Serve an OpenAI-compatible endpoint:
+
+```bash
+mlx_lm.server --model eouya2/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX
+```
+
+## Intended use
+
+This checkpoint is suitable for local Apple Silicon experimentation, Korean
+and bilingual generation, MoE pruning research, and memory-conscious inference
+where a stronger reduction in routed-expert capacity is useful. As with the
+base model, application-specific safety and quality evaluation is recommended
+before deployment.
+
+## References and acknowledgements
+
+- Base model: [`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
+- MLX 8-bit conversion: [`mlx-community/Qwen3.6-35B-A3B-8bit`](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-8bit)
+- REAP paper: [REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression](https://huggingface.co/papers/2510.13999)
+- MLX pruning implementation: [`egesabanci/reap-mlx`](https://github.com/egesabanci/reap-mlx)
+
+## License
+
+The model follows the Apache 2.0 license of the upstream Qwen release. The
+companion synthetic calibration data is released separately under CC BY 4.0.

README_ko.md

@@ -0,0 +1,120 @@
+# Qwen3.6-35B-A3B K-Guard REAP 25% — MLX 8-bit
+
+> English model card: [README.md](./README.md)
+
+이 모델은
+[`mlx-community/Qwen3.6-35B-A3B-8bit`](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-8bit)을
+기반으로 만든 한국어 중심 expert-pruned MLX 체크포인트입니다. Routed MoE
+expert에는 REAP 방식의 router-weighted activation pruning을 적용했으며,
+기존 8-bit MLX 형식, top-8 routing, shared expert, tokenizer, chat template과
+비-MoE 구성요소는 유지했습니다.
+
+이 릴리스에서 **K-Guard**는 pruning 전에 routing 및 activation 통계를
+수집할 때 사용한 한국어 중심 calibration profile을 의미합니다. 별도의
+fine-tuning이나 가중치 재학습은 하지 않았습니다.
+
+## 모델 요약
+
+| 항목 | 값 |
+|---|---:|
+| 기반 체크포인트 | `mlx-community/Qwen3.6-35B-A3B-8bit` |
+| 아키텍처 | Qwen3.6 MoE (`qwen3_5_moe`) |
+| MoE layer | 40 |
+| Layer당 routed expert | 256개에서 **192개**로 축소 |
+| Layer당 제거 expert | 64 / 256 (**25%**) |
+| Token당 활성 routed expert | 8개, 유지 |
+| Shared expert | 유지 |
+| 양자화 | MLX affine 8-bit, group size 64 |
+| 로컬 체크포인트 크기 | 약 **27.18 GiB** |
+| Pruning 후 학습 | 없음 |
+
+## Calibration 및 expert 선정
+
+총 24,576개 sequence로 구성된 결정적 한국어 중심 mixture에서 expert
+중요도를 관측했습니다.
+
+- 일반 한국어 instruction 및 reasoning 8,192개
+- 한영 의미 대응 pair 8,192개
+- 범용 capability replay 4,096개
+- Qwen3.6 text 및 reasoning 특화 4,096개
+
+Observer는 seed 17, 최대 sequence length 8,192로 40개 MoE layer 전체를
+관측했습니다. 각 layer에서 router-weighted activation 통계로 expert를
+정렬하여 상위 192개를 유지하고, router row도 동일한 index로 축소했으며,
+top-8 routing은 그대로 유지했습니다.
+
+Calibration 파일과 layer/expert별 전체 observation CSV는
+[`eouya2/KGuard-Korean-MoE-Calibration-v1`](https://huggingface.co/datasets/eouya2/KGuard-Korean-MoE-Calibration-v1)에
+공개했습니다.
+
+## 평가 결과
+
+Base와 pruning 모델 모두 동일한 deterministic subset과 prompt로
+평가했습니다.
+
+| Benchmark | Base 8-bit | 이 모델 |
+|---|---:|---:|
+| KMMLU | 66.4 | **60.9** |
+| MMLU-Pro | 64.3 | **58.8** |
+| GSM8K | 96.7 | **96.7** |
+| HumanEval+ pass@1 | 90.9 | **93.3** |
+| 학술 10-benchmark macro | 81.2 | **79.7** |
+
+KMMLU, MMLU-Pro, GSM8K는 각각 512문항의 고정 subset을 사용했고,
+HumanEval+는 EvalPlus 전체 164문항을 사용했습니다. 위 결과는 동일한
+로컬 평가 조건에서 모델 간 차이를 비교하기 위한 수치입니다.
+
+## MLX 사용법
+
+```bash
+pip install -U mlx-lm
+
+mlx_lm.generate \
+  --model eouya2/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX \
+  --prompt "한국어로 mixture-of-experts 모델을 간단히 설명해 주세요." \
+  --max-tokens 256 \
+  --temperature 0.0
+```
+
+Python 예제:
+
+```python
+from mlx_lm import generate, load
+
+model_id = "eouya2/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX"
+model, tokenizer = load(model_id)
+
+messages = [{"role": "user", "content": "한국어로 자기소개를 해 주세요."}]
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+
+print(generate(model, tokenizer, prompt=prompt, max_tokens=256))
+```
+
+OpenAI-compatible server:
+
+```bash
+mlx_lm.server --model eouya2/Qwen3.6-35B-A3B-KGuard-REAP25-8bit-MLX
+```
+
+## 권장 용도
+
+Apple Silicon 로컬 실행, 한국어·한영 생성, MoE pruning 연구, routed expert
+용량을 더 적극적으로 줄인 모델이 필요한 실험에 사용할 수 있습니다.
+실제 서비스 적용 전에는 기반 모델과 동일하게 용도별 품질 및 안전성
+평가를 권장합니다.
+
+## 참고 자료
+
+- 기반 모델: [`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
+- MLX 8-bit 변환: [`mlx-community/Qwen3.6-35B-A3B-8bit`](https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-8bit)
+- REAP 논문: [REAP the Experts](https://huggingface.co/papers/2510.13999)
+- MLX pruning 구현: [`egesabanci/reap-mlx`](https://github.com/egesabanci/reap-mlx)
+
+## 라이선스
+
+모델은 upstream Qwen 릴리스의 Apache 2.0 라이선스를 따릅니다. 별도
+공개한 합성 calibration 데이터는 CC BY 4.0입니다.

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 +1,857 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForConditionalGeneration"
+  ],
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "image_token_id": 248056,
+  "model_type": "qwen3_5_moe",
+  "quantization": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine",
+    "language_model.model.layers.0.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.6.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.9.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.12.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.18.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.21.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.24.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.30.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.33.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.36.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    }
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 8,
+    "mode": "affine",
+    "language_model.model.layers.0.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.6.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.9.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.12.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.18.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.21.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.24.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.30.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.33.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.36.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.mlp.gate": {
+      "group_size": 64,
+      "bits": 8
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "group_size": 64,
+      "bits": 8
+    }
+  },
+  "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": 2048,
+    "initializer_range": 0.02,
+    "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_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,
+    "model_type": "qwen3_5_moe_text",
+    "moe_intermediate_size": 512,
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_experts": 192,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "output_router_logits": false,
+    "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,
+      "type": "default"
+    },
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 512,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_moe",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "reap_retained_experts_by_layer": {
+    "0": 192,
+    "1": 192,
+    "2": 192,
+    "3": 192,
+    "4": 192,
+    "5": 192,
+    "6": 192,
+    "7": 192,
+    "8": 192,
+    "9": 192,
+    "10": 192,
+    "11": 192,
+    "12": 192,
+    "13": 192,
+    "14": 192,
+    "15": 192,
+    "16": 192,
+    "17": 192,
+    "18": 192,
+    "19": 192,
+    "20": 192,
+    "21": 192,
+    "22": 192,
+    "23": 192,
+    "24": 192,
+    "25": 192,
+    "26": 192,
+    "27": 192,
+    "28": 192,
+    "29": 192,
+    "30": 192,
+    "31": 192,
+    "32": 192,
+    "33": 192,
+    "34": 192,
+    "35": 192,
+    "36": 192,
+    "37": 192,
+    "38": 192,
+    "39": 192
+  },
+  "reap_primary_prune_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39
+  ]
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"visual-question-answering"}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "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
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdbdb02ce614fa85a9afd9cc291ce555e530842731f3f73f5dd8de29c6b6f4e
+size 5332384107

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c4f9fbc8f5eccd79641dcb9bd5311c824d1e11d4ce8a1d55323f22cdc53ec
+size 5190463150

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151a19edb44dbe44dc09b1ab92847e8717514788bc5dcce77ce63447d1f62bf9
+size 5223205906

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9544137d433ef8b7c827084d81b6bc29146176997629b5e132ae9ce6d99ac623
+size 5223205744

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737db04f0cf7766c037f266f32056edf94664a78d7e332f71a9f47c69e81bfac
+size 5183573833

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12b36e6958e407df64e7f137b6136112056ce880c019eeb186c1f6597c25541
+size 2113439105

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 +1,64 @@
+{
+  "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
+    ],
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_pixels": 65536,
+    "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": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "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"
+  }
+}

reap-preserved-aux-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4579339122fdc5e06774fa0c188bb5b79410a8ab821343cec7a6122a0588014
+size 893179536

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "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": "TokenizersBackend",
+  "tool_parser_type": "qwen3_coder",
+  "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"
+}