Upload native MLX-VLM 8bit MTP variant

.gitattributes

@@ -33,3 +33,5 @@ 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
+figures/Nex-N2-Benchmark-white.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: nex-agi/Nex-N2-mini
+library_name: mlx
+pipeline_tag: image-text-to-text
+tags:
+  - mlx
+  - mlx-vlm
+  - safetensors
+  - apple-silicon
+  - vision-language
+  - image-text-to-text
+  - qwen3_5_moe
+  - qwen3.5
+  - nex-n2
+  - mtp
+  - native-mtp
+  - speculative-decoding
+  - omlx
+  - 8-bit-precision
+  - conversational
+---
+
+# Nex-N2-mini-MLX-VLM-8bit-MTP
+
+Native MLX-VLM 8-bit quantized version of `nex-agi/Nex-N2-mini`, with a grafted MTP head for oMLX Native MTP speculative decoding.
+
+## Summary
+
+* Base model: `nex-agi/Nex-N2-mini`
+* Format: native MLX / MLX-VLM
+* Quantization: 8-bit MLX-VLM quantization
+* Vision: supported
+* MTP: included
+* Target runtime: oMLX with Native MTP enabled
+* Direct `mlx-vlm.generate`: not the supported runtime for this MTP variant
+
+## What changed in this version
+
+This repository uses the native MLX-VLM trunk and vision weights from `Nex-N2-mini-MLX-VLM-8bit`, while the MTP head is grafted from the `jedisct1/Nex-N2-mini-mlx-OptiQ-8bit-MTP` MTP variant.
+
+This is not the same as `jedisct1/Nex-N2-mini-mlx-OptiQ-8bit-MTP`:
+
+* This repo keeps the native MLX-VLM layout.
+* This repo includes the vision tower / VLM weights.
+* The `jedisct1` OptiQ MTP repository is text-only.
+* The MTP head is used only for speculative decoding acceleration.
+
+## Important compatibility note
+
+This MTP variant includes `language_model.mtp.*` weights intended for oMLX Native MTP.
+
+The validated runtime is:
+
+* oMLX
+* Native MTP enabled in model settings
+
+Plain `mlx-vlm.generate` or generic MLX loading paths may fail strict loading or may not use the MTP head correctly, because the preserved `language_model.mtp.*` tensors are intended for the oMLX Native MTP runtime.
+
+For direct `mlx-vlm.generate` usage, use the non-MTP variant instead:
+
+`joowon-jang/Nex-N2-mini-MLX-VLM-8bit`
+
+## Quality and behavior
+
+The MTP head is used for speculative decoding. Draft tokens are verified by the main Nex-N2-mini trunk before being accepted, so the MTP head is intended to affect speed rather than final output quality.
+
+In practice, MTP speedups depend on draft acceptance rate. The grafted head tends to help more on normal prose and reasoning, and less on unusual token sequences.
+
+## Recommended runtime
+
+Use oMLX and enable Native MTP.
+
+Suggested initial settings:
+
+* Native MTP: enabled
+* Max Draft Tokens: 2
+* Min Draft Tokens: 1
+* Temperature: 0 for benchmarking
+* Use the same prompt, context length, and max tokens when comparing against non-MTP variants
+
+## Notes
+
+This is not an OptiQ oQ8 sidecar model. The model uses a native MLX-VLM layout with `vision_tower.*` weights included in the model files.
+
+MTP head attribution:
+
+* MTP head source: `jedisct1/Nex-N2-mini-mlx-OptiQ-8bit-MTP`
+* Original base model: `nex-agi/Nex-N2-mini`
+* Donor MTP lineage described by the source model: Qwen3.5-35B-A3B MTP head grafted onto Nex-N2-mini-compatible dimensions
+
+## License
+
+Apache-2.0, following the base model and referenced MTP-head source license.

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 %}
+            {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+        {%- 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 reasoning_content %}
+            {{- '<|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>' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,901 @@
+{
+  "architectures": [
+    "Qwen3_5MoeForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "hidden_size": 2048,
+  "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
+    },
+    "language_model.mtp.layers.0.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    }
+  },
+  "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
+    },
+    "language_model.mtp.layers.0.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    },
+    "language_model.mtp.layers.0.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 128,
+      "mode": "affine"
+    }
+  },
+  "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": 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,
+    "mlp_only_layers": [],
+    "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": 256,
+    "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,
+      "rope_type": "default"
+    },
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 512,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320,
+    "quantization": {
+      "bits": 8,
+      "group_size": 64,
+      "language_model.mtp.layers.0.mlp.shared_expert.down_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.mlp.shared_expert.gate_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.mlp.shared_expert.up_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.self_attn.k_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.self_attn.q_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.self_attn.v_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      }
+    },
+    "quantization_config": {
+      "bits": 8,
+      "group_size": 64,
+      "language_model.mtp.layers.0.mlp.shared_expert.down_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.mlp.shared_expert.gate_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.mlp.shared_expert.up_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.self_attn.k_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.self_attn.q_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      },
+      "language_model.mtp.layers.0.self_attn.v_proj": {
+        "bits": 8,
+        "group_size": 128,
+        "mode": "affine"
+      }
+    }
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "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_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
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f1d108197abf4a41a8da46340672a5697d95f7c7f4e5ec0e0d948833eb5ac6
+size 5329916013

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce1ee4928dfbec2aef55509df9733524c5dc72cdf881b2a3f906423d73e3e5c
+size 5365573922

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c975b6e4dbefa731ee3ff0160420aaf920c5bf8bce01ff765a2ebf56a1090fef
+size 5358684668

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6980cb10e61b10230089288050360ce650da8b8b4e874fe619c212165d791cb
+size 5365574194

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b9e730b455502ea3e4bdf493d4ab039d22c54c21f3033ecf1eb87e947f148e
+size 5358684644

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5880f39c1a8a3a468025dcf7d4763372b5006bcc9d4584eddc2bc4c21841e1
+size 5365574174

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9104dda8f6b3ef4585c227764e5b72a89b9ef853008e43382f8d90b68e09bd
+size 5037050574

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cc1ff09601c52be4da9f5052f0c232d15b71c3c1579638ce84599fd2daa67e
+size 540344667

model-mtp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b355d970fe392a71c26e979766fcfff16f6fb2c9802bb15af73a92e937ef40d9
+size 905113956

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 +1,50 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_pixels": 65536,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "fps": 2.0,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 65536,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "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 +1,33 @@
+{
+  "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": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}