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

@@ -1,3 +1,209 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
+base_model: Qwen/Qwen3.6-27B
+base_model_relation: quantized
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- qwen3_5
+- autoround
+- int4
+- w4g128
+- w4a16
+- quantization
+- vllm
+- multimodal
+- mtp
+- speculative-decoding
+- code
+- coding
+---
+# Qwen3.6-27B INT4 AutoRound — Code Calibrated (Best Recipe)
+
+A **W4A16 (INT4 weight, FP16 activation) quantization** of [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B), produced with [Intel's AutoRound](https://github.com/intel/auto-round).
+
+> **Key difference from the standard AutoRound quant:** This variant was calibrated on a **normalized and sampled subset of [nvidia/OpenCodeInstruct](https://huggingface.co/datasets/nvidia/OpenCodeInstruct)** — a ~5 M sample, execution-verified coding dataset — instead of the default general-purpose pile corpus. Calibrating on domain-specific data guides AutoRound's weight-rounding optimization to minimize quantization error on the token distributions that matter most for code, improving accuracy on code generation, reasoning, and instruction-following for programming tasks. The **`auto-round-best` preset** was used (1000 iterations, 512 calibration samples), which runs ~4–5× slower than the standard recipe but achieves the best possible INT4 accuracy. MTP (speculative decoding) and image/vision inputs work out of the box with no post-processing required.
+
+## TL;DR
+
+- **Base**: Qwen3.6-27B (27B dense VLM)
+- **Quant**: INT4 W4A16, group_size 128, symmetric
+- **Tool**: `auto-round-best` (1000 iters, 512 samples, torch.compile)
+- **Calibration dataset**: `nvidia/OpenCodeInstruct` (coding domain)
+- **Size**: ~18 GB (down from ~54 GB BF16) — **3× reduction**
+- **MTP**: Native Multi-Token Prediction head preserved in BF16 — enables **native speculative decoding** in vLLM (~85–90% draft acceptance, ~2× throughput)
+- **Vision**: Image inputs work via the MoonViT encoder (weights kept at original BF16/FP16 precision)
+
+## Why code calibration?
+
+AutoRound's algorithm optimizes weight rounding by minimizing the difference between the quantized model's outputs and the full-precision model's outputs on a set of calibration samples. **The calibration dataset therefore shapes which activations and weight patterns are prioritized during optimization.**
+
+Using a **normalized and sampled subset of `nvidia/OpenCodeInstruct`** — a large, execution-verified dataset of coding problems and solutions — means the rounding decisions are tuned for code-style token distributions: identifiers, keywords, indentation patterns, and structured reasoning. In practice this tends to:
+
+- Better preserve accuracy on code generation benchmarks relative to a pile-calibrated quant
+- Improve instruction following for programming tasks (function signatures, docstrings, tool calls)
+- Retain structured output quality (JSON, markdown code blocks, structured diffs)
+
+If your primary use-case is code generation or an AI coding assistant, this variant is the recommended choice. For general-purpose or multimodal usage, see the standard [`Qwen3.6-27B-int4-AutoRound`](https://huggingface.co/webhie/Qwen3.6-27B-int4-AutoRound) quant.
+
+## Quick inference with vLLM (with MTP speculative decoding)
+
+Requires vLLM v0.19.1+ with Qwen3_5 MTP support. Set the following environment variables before starting:
+
+```bash
+export VLLM_USE_FLASHINFER_SAMPLER=1
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+export VLLM_FLOAT32_MATMUL_PRECISION=high
+export PYTORCH_CUDA_ALLOC_CONF="expandable_segments:True,max_split_size_mb:512"
+export VLLM_NO_USAGE_STATS=1
+export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=1
+export VLLM_MARLIN_USE_ATOMIC_ADD=1
+export OMP_NUM_THREADS=1
+export CUDA_DEVICE_MAX_CONNECTIONS=8
+export NCCL_CUMEM_ENABLE=0
+export NCCL_P2P_DISABLE=1
+```
+
+```bash
+vllm serve webhie/Qwen3.6-27B-int4-AutoRound-Code \
+  --served-model-name qwen3.6-27b \
+  --host 0.0.0.0 --port 11434 \
+  --trust-remote-code \
+  --dtype auto \
+  --quantization auto_round \
+  --max-model-len 200704 \
+  --gpu-memory-utilization 0.92 \
+  --max-num-seqs 4 \
+  --kv-cache-dtype fp8_e4m3 \
+  --attention-backend flashinfer \
+  --performance-mode throughput \
+  --max-num-batched-tokens 2048 \
+  --enable-chunked-prefill \
+  --enable-auto-tool-choice \
+  --tool-call-parser qwen3_coder \
+  --reasoning-parser qwen3 \
+  --default-chat-template-kwargs '{"preserve_thinking":true}' \
+  --override-generation-config '{"temperature":0.6,"top_p":0.95,"top_k":20,"min_p":0.0,"presence_penalty":0.0,"repetition_penalty":1.0}' \
+  --enable-prompt-tokens-details \
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
+```
+
+Remove `--speculative-config` to disable MTP speculative decoding. See the [vllm-blackwell-guide](https://github.com/lastloop-ai/vllm-blackwell-guide) repo for a full Docker Compose setup with all env vars pre-configured.
+
+### OpenAI-compatible request
+
+```python
+from openai import OpenAI
+client = OpenAI(base_url="http://localhost:11434/v1", api_key="EMPTY")
+r = client.chat.completions.create(
+    model="qwen3.6-27b",
+    messages=[{"role": "user", "content": "Write a quicksort in Python."}],
+    max_tokens=512,
+)
+print(r.choices[0].message.content)
+```
+
+### Transformers (no spec decoding)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+m = AutoModelForCausalLM.from_pretrained(
+    "webhie/Qwen3.6-27B-int4-AutoRound-Code",
+    trust_remote_code=True,
+    device_map="auto",
+)
+tok = AutoTokenizer.from_pretrained("webhie/Qwen3.6-27B-int4-AutoRound-Code")
+msg = [{"role": "user", "content": "Write a binary search in Python."}]
+ids = tok.apply_chat_template(msg, add_generation_prompt=True, return_tensors="pt").to(m.device)
+print(tok.decode(m.generate(ids, max_new_tokens=256)[0]))
+```
+
+## Quantization details
+
+| Field | Value |
+|---|---|
+| Base | `Qwen/Qwen3.6-27B` |
+| Method | AutoRound (`intel/auto-round`), **best recipe** |
+| Scheme | W4A16 (4-bit weights, FP16 activations) |
+| Bits | 4 |
+| Group size | 128 |
+| Symmetric | yes |
+| Packing format | `auto_round:auto_gptq` |
+| Unquantized layers | `linear_attn.in_proj_a/b`, all LayerNorms, RMSNorms, router gates |
+| Calibration dataset | Normalized & sampled subset of [`nvidia/OpenCodeInstruct`](https://huggingface.co/datasets/nvidia/OpenCodeInstruct) |
+| Calibration samples | 512 |
+| Iterations | 1000 |
+| torch.compile | enabled |
+| GPU used for quant | 1× RTX 5090 (32 GB, SM120), `low_gpu_mem_usage=True` |
+
+### Unquantized layers — why
+
+- **`linear_attn.in_proj_a/b`**: low-rank projections in Qwen3.6's Gated DeltaNet whose shapes aren't divisible by 32 (group_size), so AutoRound skips them automatically. Tiny fraction of total parameters.
+- **Norms, routers**: precision-sensitive and very small — kept at full precision.
+
+## Performance
+
+Benchmarked on **1× RTX 5090 (32 GB)** with vLLM + FP8 KV cache + MTP n=3:
+
+| Config | Throughput |
+|---|---:|
+| vLLM + MTP n=3 | **~150 tok/s** |
+| vLLM (MTP disabled) | **~70 tok/s** |
+
+The ~2× speedup comes from ~85–90% draft acceptance via MTP speculative decoding with `num_speculative_tokens: 3`.
+
+## Reproduction
+
+```bash
+pip install auto-round
+
+# The calibration data was first normalized and sampled from nvidia/OpenCodeInstruct
+# (formatting cleaned, deduplicated, balanced across domains) and exported as a
+# local JSON file before quantization. Pass your own prepared subset with:
+# --dataset ./subset_10k.json
+
+auto-round-best \
+  --model Qwen/Qwen3.6-27B \
+  --scheme W4A16 \
+  --format auto_round \
+  --output_dir Qwen3.6-27B-int4-AutoRound-Code \
+  --enable_torch_compile \
+  --low_gpu_mem_usage \
+  --device_map 0
+```
+
+No post-processing needed — MTP and image inputs work out of the box.
+
+## Acknowledgements
+
+- [Alibaba / Qwen team](https://huggingface.co/Qwen) for the base [Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) model
+- [Intel AutoRound](https://github.com/intel/auto-round) team for the quantization framework and the `auto-round-best` recipe
+- [NVIDIA](https://huggingface.co/nvidia) for the [OpenCodeInstruct](https://huggingface.co/datasets/nvidia/OpenCodeInstruct) calibration dataset — ~5 M execution-verified coding samples used to domain-adapt this quant
+- [Lorbus](https://huggingface.co/Lorbus) for the original AutoRound quant of this model that inspired this release
+- [@eugr](https://github.com/eugr) for the [spark-vllm-docker](https://github.com/eugr/spark-vllm-docker) fork and TurboQuant KV cache work
+- [vLLM project](https://github.com/vllm-project/vllm) for the inference engine and Qwen3_5 MTP support
+
+## License
+
+Apache 2.0 — same as [Qwen3.6-27B base](https://huggingface.co/Qwen/Qwen3.6-27B).
+
+## Citation
+
+If you use this quant, please cite the original Qwen3.6 release (see base model card), the AutoRound paper, and the OpenCodeInstruct dataset:
+
+```bibtex
+@article{cheng2023autoround,
+  title   = {Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs},
+  author  = {Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi},
+  journal = {arXiv preprint arXiv:2309.05516},
+  year    = {2023}
+}
+
+@misc{nvidia2025opencode,
+  title  = {OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs},
+  author = {NVIDIA},
+  year   = {2025},
+  url    = {https://huggingface.co/datasets/nvidia/OpenCodeInstruct}
+}
+```

chat_template.jinja

@@ -0,0 +1,230 @@
+{%- 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 is defined and 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 is defined and 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 %}
+{%- set ns_flags = namespace(enable_thinking=true, has_tools=false) %}
+{%- if enable_thinking is defined %}
+    {%- set ns_flags.enable_thinking = enable_thinking %}
+{%- endif %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set system_content = '' %}
+{%- set has_system = false %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set has_system = true %}
+    {%- set system_content = render_content(messages[0].content, false, true)|trim %}
+    {%- if '<|think_off|>' in system_content %}
+        {%- set ns_flags.enable_thinking = false %}
+        {%- set system_content = system_content | replace('<|think_off|>', '') %}
+    {%- endif %}
+    {%- if '<|think_on|>' in system_content %}
+        {%- set ns_flags.enable_thinking = true %}
+        {%- set system_content = system_content | replace('<|think_on|>', '') %}
+    {%- endif %}
+    {%- set system_content = system_content | trim %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {%- set ns_flags.has_tools = true %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {%- set fn = tool.function if tool.function is defined else tool %}
+        {%- set props = {} %}
+        {%- set req = [] %}
+        {%- if fn.parameters is defined and fn.parameters is mapping %}
+            {%- if fn.parameters.properties is defined %}
+                {%- set props = fn.parameters.properties %}
+            {%- endif %}
+            {%- if fn.parameters.required is defined %}
+                {%- set req = fn.parameters.required %}
+            {%- endif %}
+        {%- endif %}
+        {%- set ns_p = namespace(sig='') %}
+        {%- for pname in props %}
+            {%- set pdef = props[pname] %}
+            {%- set ptype = 'any' %}
+            {%- if pdef.type is defined %}
+                {%- if pdef.type == 'array' or pdef.type == 'object' %}
+                    {%- set ptype = 'array|object' %}
+                {%- elif pdef.enum is defined and pdef.enum is iterable and pdef.enum is not string and pdef.enum is not mapping %}
+                    {%- set ptype = pdef.enum | join('|') %}
+                {%- else %}
+                    {%- set ptype = pdef.type %}
+                {%- endif %}
+            {%- endif %}
+            {%- set part = pname ~ ('' if pname in req else '?') ~ ': ' ~ ptype %}
+            {%- set ns_p.sig = ns_p.sig ~ ', ' ~ part if ns_p.sig else part %}
+        {%- endfor %}
+        {{- '\n- ' ~ fn.name ~ '(' ~ ns_p.sig ~ ')' }}
+        {%- if fn.description is defined %}
+            {{- ' — ' ~ fn.description }}
+        {%- endif %}
+        {%- if fn.parameters is defined and fn.parameters is mapping %}
+            {%- for pname in props %}
+                {%- set pdef = props[pname] %}
+                {%- if pdef.type is defined and (pdef.type == 'array' or pdef.type == 'object') %}
+                    {{- '\n  - ' ~ pname ~ ' schema: ' ~ pdef | tojson }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- 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>' }}
+    {%- if has_system and system_content %}
+        {{- '\n\n' + system_content }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- elif has_system and system_content %}
+    {{- '<|im_start|>system\n' + system_content + '<|im_end|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set is_system = (message.role == "system" or message.role == "developer") %}
+    {%- set content = render_content(message.content, true, is_system)|trim %}
+    {%- if '<|think_off|>' in content %}
+        {%- set ns_flags.enable_thinking = false %}
+        {%- set content = content | replace('<|think_off|>', '') | trim %}
+    {%- elif '<|think_on|>' in content %}
+        {%- set ns_flags.enable_thinking = true %}
+        {%- set content = content | replace('<|think_on|>', '') | trim %}
+    {%- endif %}
+    {%- if is_system %}
+        {%- if not loop.first and content %}
+            {{- '<|im_start|>system\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 or '</thinking>' in content %}
+                {%- set think_end_token = '</think>' if '</think>' in content else '</thinking>' %}
+                {%- set reasoning_parts = content.split(think_end_token) %}
+                {%- set reasoning_content = reasoning_parts[0] %}
+                {%- set content = reasoning_parts[1] %}
+                {%- if '<think>' in reasoning_content %}
+                    {%- set reasoning_content = reasoning_content.split('<think>')[1] %}
+                {%- endif %}
+            {%- elif '<think>' in content %}
+                {%- if '<tool_call>' in content %}
+                    {%- set content = content | replace('<tool_call>', '</think>\n<tool_call>', 1) %}
+                    {%- set reasoning_parts = content.split('</think>') %}
+                    {%- set reasoning_content = reasoning_parts[0] %}
+                    {%- set content = reasoning_parts[1] %}
+                    {%- if '<think>' in reasoning_content %}
+                        {%- set reasoning_content = reasoning_content.split('<think>')[1] %}
+                    {%- endif %}
+                {%- else %}
+                    {%- set reasoning_content = content.split('<think>')[1] %}
+                    {%- set content = '' %}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content | trim %}
+        {%- set content = content | trim %}
+        {%- set show_think = false %}
+        {%- if reasoning_content %}
+            {%- if preserve_thinking is defined and preserve_thinking %}
+                {%- set show_think = true %}
+            {%- elif loop.last %}
+                {%- set show_think = true %}
+            {%- endif %}
+        {%- endif %}
+        {%- if show_think %}
+            {{- '<|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 and content %}
+                    {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined and tool_call.arguments is mapping %}
+                    {%- if tool_call.arguments|length > 0 %}
+                        {%- for args_name in tool_call.arguments %}
+                            {%- set args_value = tool_call.arguments[args_name] %}
+                            {{- '<parameter=' + args_name + '>\n' }}
+                            {%- set args_value = args_value | tojson if args_value is mapping or (args_value is iterable and args_value is not string) else args_value | string %}
+                            {{- args_value }}
+                            {{- '\n</parameter>\n' }}
+                        {%- endfor %}
+                    {%- endif %}
+                {%- elif tool_call.arguments is defined and tool_call.arguments is string %}
+                    {%- if tool_call.arguments|trim|length > 0 %}
+                        {{- tool_call.arguments }}
+                        {{- '\n' }}
+                    {%- endif %}
+                {%- 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 ns_flags.enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,548 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "quantization_config": {
+    "autoround_version": "0.13.0",
+    "bits": 4,
+    "block_name_to_quantize": [
+      "model.language_model.layers",
+      "mtp.layers"
+    ],
+    "data_type": "int",
+    "extra_config": {
+      "model.language_model.layers.0.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.0.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.1.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.1.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.10.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.10.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.12.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.12.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.13.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.13.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.14.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.14.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.16.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.16.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.17.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.17.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.18.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.18.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.2.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.2.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.20.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.20.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.21.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.21.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.22.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.22.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.24.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.24.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.25.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.25.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.26.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.26.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.28.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.28.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.29.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.29.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.30.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.30.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.32.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.32.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.33.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.33.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.34.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.34.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.36.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.36.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.37.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.37.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.38.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.38.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.4.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.4.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.40.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.40.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.41.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.41.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.42.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.42.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.44.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.44.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.45.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.45.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.46.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.46.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.48.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.48.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.49.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.49.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.5.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.5.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.50.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.50.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.52.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.52.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.53.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.53.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.54.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.54.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.56.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.56.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.57.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.57.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.58.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.58.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.6.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.6.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.60.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.60.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.61.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.61.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.62.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.62.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.8.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.8.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.9.linear_attn.in_proj_a": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "model.language_model.layers.9.linear_attn.in_proj_b": {
+        "bits": 16,
+        "data_type": "fp"
+      },
+      "mtp.fc": {
+        "bits": 16,
+        "data_type": "fp"
+      }
+    },
+    "group_size": 128,
+    "iters": 1000,
+    "low_gpu_mem_usage": true,
+    "nsamples": 512,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
+  },
+  "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": "5.8.0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.8.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5f31382db1faf18a5bc32a8892c6b5143a5a0f2bb1e552f8844f7ab5f3c947
+size 3216489680

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5542d5c232efb98d64e3fc4e9210111d32e2b4a23272a2d7c02e18004f07ab60
+size 3190151576

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211ce8a9b7899221ccd414a15a1e2bdc550b118d9938302108e4f8579f423d94
+size 3219130488

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ea3aecda21080c0486d0a26c31b34caf83b154cf97652d7c33752f96372712
+size 3216860120

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517ead0081fdcb0113a6a881dfabadaa1159874298c06f22c802889d67e0613f
+size 770164464

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9b80896068ddd0a9603b93e5fa0c34673131cc25123f980ad34512e0399a2a
+size 2542807272

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abed7b0a601b5837427b299e44faad8ad0ec64bdce16da2147736eeff4bb86a9
+size 2542796896

model_extra_tensors.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1981cfd8decc58e5f3e7e067c65983e8753fc1587110a420d14ba7b87ecca557
+size 298305576

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "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_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"
+  }
+}

quantization_config.json

@@ -0,0 +1,399 @@
+{
+  "bits": 4,
+  "data_type": "int",
+  "group_size": 128,
+  "sym": true,
+  "iters": 1000,
+  "low_gpu_mem_usage": true,
+  "nsamples": 512,
+  "autoround_version": "0.13.0",
+  "block_name_to_quantize": "model.language_model.layers",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq",
+  "extra_config": {
+    "model.language_model.layers.0.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.0.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.1.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.1.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.2.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.2.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.4.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.4.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.5.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.5.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.6.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.6.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.8.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.8.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.9.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.9.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.10.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.10.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.12.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.12.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.13.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.13.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.14.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.14.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.16.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.16.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.17.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.17.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.18.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.18.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.20.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.20.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.21.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.21.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.22.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.22.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.24.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.24.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.25.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.25.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.26.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.26.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.28.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.28.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.29.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.29.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.30.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.30.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.32.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.32.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.33.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.33.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.34.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.34.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.36.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.36.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.37.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.37.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.38.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.38.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.40.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.40.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.41.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.41.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.42.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.42.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.44.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.44.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.45.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.45.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.46.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.46.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.48.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.48.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.49.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.49.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.50.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.50.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.52.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.52.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.53.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.53.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.54.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.54.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.56.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.56.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.57.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.57.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.58.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.58.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.60.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.60.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.61.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.61.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.62.linear_attn.in_proj_b": {
+      "bits": 16,
+      "data_type": "fp"
+    },
+    "model.language_model.layers.62.linear_attn.in_proj_a": {
+      "bits": 16,
+      "data_type": "fp"
+    }
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

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": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}