Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16
+base_model_relation: quantized
+library_name: vllm
+tags:
+  - nvfp4
+  - compressed-tensors
+  - mtp
+  - speculative-decoding
+  - blackwell
+  - qwen3_5
+  - uncensored
+pipeline_tag: text-generation
+---
+
+# Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4
+
+NVFP4 (W4A4, group 16) quantization of [**AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16**](https://huggingface.co/AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16) — all credit for the model itself goes to [@AEON-7](https://huggingface.co/AEON-7). This repo only carries the quantized weights.
+
+**55.6 GB → 20.58 GB.** Fits on two 16 GB cards with real KV headroom.
+
+- **MTP draft head preserved in bf16** and wired into the index — speculative decoding works out of the box.
+- bf16 kept for: `lm_head`, the vision tower, the DeltaNet `conv1d`, and the MTP head. Everything else is NVFP4 W4A4.
+- Built for **SM120 / Blackwell with vanilla vLLM v0.22.0** — compressed-tensors is auto-detected, no `--quantization` flag.
+- Quantized GPU-resident (full bf16 dispatched across 7× RTX PRO 2000 Blackwell via `device_map=auto`): **122 seconds end to end.**
+
+## Measured (TP=4, 32k ctx, KV fp8, RTX PRO 2000 Blackwell ×4, MTP n=3)
+
+| concurrency | aggregate t/s |
+|---|---|
+| 1 | 69.0 |
+| 4 | 202.3 |
+| 8 | 377.8 |
+
+Single-stream prefill: **3,720 tok/s** (best 3,888) on an 8k prompt, prefix cache disabled, mean of 3. GPU KV cache at this config: 619,613 tokens.
+
+Sanity-checked after quantization: Japanese self-introduction, arithmetic/primality, and Python code generation all come back clean — no structural damage from the 4-bit pass.
+
+## Serve
+
+```bash
+vllm serve sakamakismile/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4 \
+  --trust-remote-code --tensor-parallel-size 4 \
+  --max-model-len 32768 --kv-cache-dtype fp8 --reasoning-parser qwen3 \
+  --speculative-config '{"method":"qwen3_5_mtp","num_speculative_tokens":3}'
+```
+
+On boards without P2P add `NCCL_P2P_DISABLE=1` and `--disable-custom-all-reduce`.
+
+## ⚠️ Gotchas
+
+- **The 15 `mtp.*` modules are listed in `quantization_config.ignore` — do not remove them.** If vLLM treats the bf16 MTP head as NVFP4 the draft breaks silently: 0% acceptance, slower than no MTP at all.
+- W4A16 (NVFP4A16) does **not** serve on this architecture in vLLM 0.22 (`gptq_marlin_repack: size_n=24 not divisible by tile_n_size=64`). W4A4 only.
+- Reasoning model: give it `max_tokens ≥ 4096`, or use `chat_template_kwargs: {"reasoning_effort": "low"}` for long-form generation — at the default effort it can spend the entire budget thinking.
+- Long single-file code generation drops a closing paren roughly 1–2 times in 14 regardless of sampling temperature (measured with a JS parser on the base Qwen3.8-27B). Put a syntax check in the loop rather than tuning temperature.
+
+## Recipe
+
+llm-compressor NVFP4 (W4A4, group 16), `targets: [Linear]`, `ignore: [lm_head, re:.*visual.*, re:.*conv1d.*, re:.*mtp.*]`, 32 calibration samples × 8192 tok from `neuralmagic/calibration`. MTP tensors grafted back in bf16 after saving and appended to `quantization_config.ignore`.
+
+🙏 [@AEON-7](https://huggingface.co/AEON-7) for the model, Qwen team for the base, vLLM & llm-compressor teams for the tooling.

chat_template.jinja

@@ -0,0 +1,170 @@
+{%- 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 %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# 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 %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|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 %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or 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 and tool_call.arguments != '' %}
+                    {%- 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 +1,413 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "nvfp4-pack-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.language_model.layers.0.linear_attn",
+      "model.language_model.layers.0.linear_attn.norm",
+      "model.language_model.layers.1.linear_attn",
+      "model.language_model.layers.1.linear_attn.norm",
+      "model.language_model.layers.2.linear_attn",
+      "model.language_model.layers.2.linear_attn.norm",
+      "model.language_model.layers.4.linear_attn",
+      "model.language_model.layers.4.linear_attn.norm",
+      "model.language_model.layers.5.linear_attn",
+      "model.language_model.layers.5.linear_attn.norm",
+      "model.language_model.layers.6.linear_attn",
+      "model.language_model.layers.6.linear_attn.norm",
+      "model.language_model.layers.8.linear_attn",
+      "model.language_model.layers.8.linear_attn.norm",
+      "model.language_model.layers.9.linear_attn",
+      "model.language_model.layers.9.linear_attn.norm",
+      "model.language_model.layers.10.linear_attn",
+      "model.language_model.layers.10.linear_attn.norm",
+      "model.language_model.layers.12.linear_attn",
+      "model.language_model.layers.12.linear_attn.norm",
+      "model.language_model.layers.13.linear_attn",
+      "model.language_model.layers.13.linear_attn.norm",
+      "model.language_model.layers.14.linear_attn",
+      "model.language_model.layers.14.linear_attn.norm",
+      "model.language_model.layers.16.linear_attn",
+      "model.language_model.layers.16.linear_attn.norm",
+      "model.language_model.layers.17.linear_attn",
+      "model.language_model.layers.17.linear_attn.norm",
+      "model.language_model.layers.18.linear_attn",
+      "model.language_model.layers.18.linear_attn.norm",
+      "model.language_model.layers.20.linear_attn",
+      "model.language_model.layers.20.linear_attn.norm",
+      "model.language_model.layers.21.linear_attn",
+      "model.language_model.layers.21.linear_attn.norm",
+      "model.language_model.layers.22.linear_attn",
+      "model.language_model.layers.22.linear_attn.norm",
+      "model.language_model.layers.24.linear_attn",
+      "model.language_model.layers.24.linear_attn.norm",
+      "model.language_model.layers.25.linear_attn",
+      "model.language_model.layers.25.linear_attn.norm",
+      "model.language_model.layers.26.linear_attn",
+      "model.language_model.layers.26.linear_attn.norm",
+      "model.language_model.layers.28.linear_attn",
+      "model.language_model.layers.28.linear_attn.norm",
+      "model.language_model.layers.29.linear_attn",
+      "model.language_model.layers.29.linear_attn.norm",
+      "model.language_model.layers.30.linear_attn",
+      "model.language_model.layers.30.linear_attn.norm",
+      "model.language_model.layers.32.linear_attn",
+      "model.language_model.layers.32.linear_attn.norm",
+      "model.language_model.layers.33.linear_attn",
+      "model.language_model.layers.33.linear_attn.norm",
+      "model.language_model.layers.34.linear_attn",
+      "model.language_model.layers.34.linear_attn.norm",
+      "model.language_model.layers.36.linear_attn",
+      "model.language_model.layers.36.linear_attn.norm",
+      "model.language_model.layers.37.linear_attn",
+      "model.language_model.layers.37.linear_attn.norm",
+      "model.language_model.layers.38.linear_attn",
+      "model.language_model.layers.38.linear_attn.norm",
+      "model.language_model.layers.40.linear_attn",
+      "model.language_model.layers.40.linear_attn.norm",
+      "model.language_model.layers.41.linear_attn",
+      "model.language_model.layers.41.linear_attn.norm",
+      "model.language_model.layers.42.linear_attn",
+      "model.language_model.layers.42.linear_attn.norm",
+      "model.language_model.layers.44.linear_attn",
+      "model.language_model.layers.44.linear_attn.norm",
+      "model.language_model.layers.45.linear_attn",
+      "model.language_model.layers.45.linear_attn.norm",
+      "model.language_model.layers.46.linear_attn",
+      "model.language_model.layers.46.linear_attn.norm",
+      "model.language_model.layers.48.linear_attn",
+      "model.language_model.layers.48.linear_attn.norm",
+      "model.language_model.layers.49.linear_attn",
+      "model.language_model.layers.49.linear_attn.norm",
+      "model.language_model.layers.50.linear_attn",
+      "model.language_model.layers.50.linear_attn.norm",
+      "model.language_model.layers.52.linear_attn",
+      "model.language_model.layers.52.linear_attn.norm",
+      "model.language_model.layers.53.linear_attn",
+      "model.language_model.layers.53.linear_attn.norm",
+      "model.language_model.layers.54.linear_attn",
+      "model.language_model.layers.54.linear_attn.norm",
+      "model.language_model.layers.56.linear_attn",
+      "model.language_model.layers.56.linear_attn.norm",
+      "model.language_model.layers.57.linear_attn",
+      "model.language_model.layers.57.linear_attn.norm",
+      "model.language_model.layers.58.linear_attn",
+      "model.language_model.layers.58.linear_attn.norm",
+      "model.language_model.layers.60.linear_attn",
+      "model.language_model.layers.60.linear_attn.norm",
+      "model.language_model.layers.61.linear_attn",
+      "model.language_model.layers.61.linear_attn.norm",
+      "model.language_model.layers.62.linear_attn",
+      "model.language_model.layers.62.linear_attn.norm",
+      "lm_head",
+      "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": "0.17.1"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "output_gate_type": "swish",
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1+solaropen2",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.14.1+solaropen2"
+}

model-mtp-bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fa0e3eed5a647c035c6df9ecabc416c0f8d573ff84ac12485b085f00a7cdf2
+size 849400424

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca4957d492e9ac0cdf77d79a2f7809482924588cd42cbb589990c6c11efbc2a
+size 19709883808

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"
+  }
+}

recipe.yaml

@@ -0,0 +1,7 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: [lm_head, 're:.*visual.*', 're:.*conv1d.*', 're:.*mtp.*']
+      scheme: NVFP4
+      bypass_divisibility_checks: false

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445a1c450cb82eba3dac6d4cac5d6ce9a6be0ab6e326bf919934d71e604a871f
+size 19989424

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "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,
+  "max_length": null,
+  "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_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

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"
+}