Add GPU-validated Qwen3.8 Flash-Next tiny random model

.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

.meta.json

@@ -0,0 +1,18 @@
+{
+  "Pillow": "12.2.0",
+  "accelerate": "1.15.0",
+  "av": "19.0.2",
+  "flashinfer-python": "0.7.2",
+  "huggingface_hub": "1.33.0",
+  "kernels": "0.17.0",
+  "numpy": "2.3.5",
+  "safetensors": "0.8.0",
+  "sglang": "0.5.23.dev384+g9ab74b851",
+  "tiny-random": "0.2.0",
+  "torch": "2.14.1",
+  "torchcodec": "0.17.0",
+  "transformers": "5.19.0",
+  "Python": "3.12.13",
+  "CUDA": "13.0",
+  "libstdc++": "13.4.0"
+}

README.md

@@ -0,0 +1,182 @@
+---
+library_name: transformers
+base_model:
+- Qwen/Qwen3.8-Flash-Next-FP8
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [Qwen/Qwen3.8-Flash-Next-FP8](https://huggingface.co/Qwen/Qwen3.8-Flash-Next-FP8).
+
+Structural comparison with `Qwen/Qwen3.8-Flash-Next-FP8`:
+
+| Feature | Source | Tiny |
+|---|---|---|
+| Architecture / modalities | Qwen4Exp; text, image, video | Same |
+| Vocabulary / tied embeddings | 248,320 / false | Same |
+| Backbone layers / hidden size | 48 / 2,560 | 8 / 32 |
+| Attention Q/KV heads; head dim | 24/2; 256 | 12/1; 32 |
+| Attention cycle | 3 linear + 1 QSA | Same; two cycles |
+| Linear key/value heads; head dim | 16/48; 128 | 4/12; 32 |
+| Routed experts / top-k | 512 / 10 | 32 / 10 |
+| Expert/shared intermediate size | 640 / 640 | 128 / 128 |
+| Hyper-Connections / mixing rank | 4 / 320 | 4 / 4 |
+| QSA heads / dimension / token budget / compression | 4 / 128 / 2,048 / 4 | Same |
+| PLE layer / n-gram orders / heads per order | 2 / 2,3 / 8 | Same |
+| PLE rows / embedding columns / dtype | 320,001,536 / 160 / FP8 | 9,216 / 1 / FP8 |
+| PLE hash bucket base | 20,000,000 | 512; official prime layout |
+| PLE convolution / serialized table shards | 4 / 128 | Same |
+| MTP | 1 QSA layer; HC fusion; shared token embeddings | Same |
+| Vision depth / hidden size / output size | 27 / 1,152 / 2,560 | 2 / 64 / 32 |
+| Vision patch / temporal patch / merge | 16 / 2 / 2 | Same |
+
+PLE retains the source n-gram orders, head count, hash/prime-layout algorithm,
+projections and convolution with reduced auxiliary hash capacity. The main token
+vocabulary and IDs are unchanged.
+The two untied BF16 token embedding/head matrices at width 32 alone occupy
+31,784,960 bytes, exceeding the 30 MB target. This native block-FP8 backend
+requires width 32; the complete checkpoint is 37,655,018 bytes. Routed experts
+retain FP8 with 32x32 blocks and BF16 scales; PLE retains FP8 and one BF16 scale.
+Tokenizer and processor assets are copied unchanged from the pinned source.
+
+| File path | Size |
+|------|------|
+| model.safetensors | 37.7MB |
+
+
+### Example usage:
+
+- SGLang
+
+  - Run on both two-GPU nodes with NODE_RANK set to 0 or 1, the same
+    DIST_INIT_ADDR, and an available local NCCL_PORT. Enables TP=4, NEXTN/MTP
+    and CUDA Graph.
+  - Verified on four NVIDIA H20 GPUs across two nodes for text, QSA long
+    prompts, image-plus-text and video-plus-text; see Test environment.
+
+```bash
+model_id=tiny-random/qwen3.8-flash-next-fp8
+node_rank=${NODE_RANK:-0}
+dist_init_addr=${DIST_INIT_ADDR}
+nccl_port=${NCCL_PORT}
+sglang serve \
+  --model-path $model_id \
+  --tp-size 4 \
+  --nnodes 2 \
+  --node-rank $node_rank \
+  --dist-init-addr $dist_init_addr \
+  --nccl-port $nccl_port \
+  --fp8-gemm-backend triton \
+  --moe-runner-backend triton \
+  --speculative-algorithm NEXTN \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --context-length 4096 \
+  --max-total-tokens 4096 \
+  --chunked-prefill-size 512 \
+  --mem-fraction-static 0.4 \
+  --cuda-graph-config '{"decode": {"bs": [1, 2, 4, 8]}}' \
+  --disable-custom-all-reduce
+```
+
+- Transformers
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoProcessor, Qwen4ExpForConditionalGeneration
+
+model_id = "tiny-random/qwen3.8-flash-next-fp8"
+model = Qwen4ExpForConditionalGeneration.from_pretrained(
+    model_id, dtype=torch.bfloat16, device_map="cuda", attn_implementation="sdpa",
+)
+processor = AutoProcessor.from_pretrained(model_id)
+messages = [{"role": "user", "content": [
+    {"type": "image", "image": Image.new("RGB", (64, 64), (220, 30, 30))},
+    {"type": "text", "text": "Describe this image."},
+]}]
+inputs = processor.apply_chat_template(
+    messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",
+).to(model.device)
+output = model.generate(**inputs, do_sample=False, max_new_tokens=10)
+print(processor.decode(output[0, inputs['input_ids'].shape[1]:], skip_special_tokens=True))
+```
+
+### Codes to create this repo:
+
+<details><summary>Click to expand</summary>
+
+```python
+import json
+from pathlib import Path
+
+import torch
+from huggingface_hub import hf_hub_download
+from transformers import AutoConfig, AutoModelForImageTextToText, set_seed
+# Creation helpers: pip install git+https://github.com/yujiepan/tiny-random.git
+from tiny_random.qwen_utils import add_qwen4_mtp, copy_qwen_source_assets, save_random_qwen_checkpoint
+
+source_model_id = "Qwen/Qwen3.8-Flash-Next-FP8"
+save_folder = "/tmp/tiny-random/qwen38-flash-next-fp8"
+source_revision = '236dfdf285828023ca3bcd3f37366c58a3469b13'
+set_seed(42)
+folder = Path(save_folder)
+folder.mkdir(parents=True, exist_ok=True)
+raw = json.loads(Path(hf_hub_download(source_model_id, 'config.json', revision=source_revision)).read_text())
+quantization = raw.pop('quantization_config')
+quantization['weight_block_size'] = [32, 32]
+raw['text_config'].update(
+    hidden_size=32, ple_embed_dim=16, ngram_vocab_size_base=512, hc_lowrank=4, num_hidden_layers=8,
+    layer_types=(["linear_attention"] * 3 + ["full_attention"]) * 2,
+    num_attention_heads=12, num_key_value_heads=1, head_dim=32,
+    linear_num_key_heads=4, linear_num_value_heads=12,
+    linear_key_head_dim=32, linear_value_head_dim=32,
+    num_experts=32, moe_intermediate_size=128, shared_expert_intermediate_size=128,
+)
+raw['text_config']['rope_parameters']['mrope_section'] = [2, 1, 1]
+raw['vision_config'].update(depth=2, hidden_size=64, intermediate_size=128, num_heads=4, out_hidden_size=32)
+(folder / 'config.json').write_text(json.dumps(raw, indent=2))
+config = AutoConfig.from_pretrained(folder)
+model = AutoModelForImageTextToText.from_config(config, dtype=torch.bfloat16)
+add_qwen4_mtp(model, model.model.language_model)
+save_random_qwen_checkpoint(model, folder, quantization)
+raw['quantization_config'] = quantization
+(folder / 'config.json').write_text(json.dumps(raw, indent=2))
+copy_qwen_source_assets(source_model_id, source_revision, folder)
+```
+
+</details>
+
+### Printing the model:
+
+<details><summary>Click to expand</summary>
+
+```text
+Qwen3.8 Flash-Next: 8 backbone layers + 1 HC-aware MTP layer; hidden_size=32
+```
+
+</details>
+
+### Test environment:
+
+- Pillow: 12.2.0
+- accelerate: 1.15.0
+- av: 19.0.2
+- flashinfer-python: 0.7.2
+- huggingface_hub: 1.33.0
+- kernels: 0.17.0
+- numpy: 2.3.5
+- safetensors: 0.8.0
+- sglang: 0.5.23.dev384+g9ab74b851
+- tiny-random: 0.2.0
+- torch: 2.14.1
+- torchcodec: 0.17.0
+- transformers: 5.19.0
+- Python: 3.12.13
+- CUDA: 13.0
+- libstdc++: 13.4.0
+
+### Change log:
+
+- 2026-10-23: Initial version.
+
+This repo is generated by GPT-6.1-Sol

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 +1,302 @@
+{
+  "architectures": [
+    "Qwen4ExpForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen4_exp",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "hc_count": 4,
+    "hc_lowrank": 4,
+    "head_dim": 32,
+    "heads_per_ngram": 8,
+    "hidden_act": "silu",
+    "hidden_size": 32,
+    "indexer_budget": 2048,
+    "indexer_compress_ratio": 4,
+    "indexer_head_dim": 128,
+    "indexer_kv_heads": 1,
+    "indexer_n_heads": 4,
+    "initializer_range": 0.02,
+    "layer_types": [
+      "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": 32,
+    "linear_num_key_heads": 4,
+    "linear_num_value_heads": 12,
+    "linear_value_head_dim": 32,
+    "make_ngram_vocab_size_divisible_by": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen4_exp_text",
+    "moe_intermediate_size": 128,
+    "mtp": {
+      "hybrid": true,
+      "layer_types": [
+        "full_attention"
+      ],
+      "mtp_use_hidden_state_from_layer": null,
+      "num_hidden_layers": 1,
+      "rope_theta": 10000000
+    },
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "ngram_size": 3,
+    "ngram_vocab_size_base": 512,
+    "num_attention_heads": 12,
+    "num_experts": 32,
+    "num_experts_per_tok": 10,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 1,
+    "output_gate_type": "sigmoid",
+    "output_router_logits": false,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "ple_conv_kernel_size": 4,
+    "ple_embed_dim": 16,
+    "ple_layer_ids": [
+      2
+    ],
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        2,
+        1,
+        1
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 128,
+    "split_ngram_parts": 128,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0.dev0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 2,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 64,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 128,
+    "model_type": "qwen4_exp",
+    "num_heads": 4,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 32,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "quantization_config": {
+    "quant_method": "fp8",
+    "activation_scheme": "dynamic",
+    "weight_per_tensor": false,
+    "act_per_tensor": false,
+    "weight_block_size": [
+      32,
+      32
+    ],
+    "modules_to_not_convert": [
+      "lm_head",
+      "model.language_model.embed_tokens",
+      "model.language_model.hyper_connection_mixer.input_mix_weight_down",
+      "model.language_model.hyper_connection_mixer.input_mix_weight_up",
+      "model.language_model.layers.0.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.0.linear_attn.conv1d",
+      "model.language_model.layers.0.linear_attn.in_proj_a",
+      "model.language_model.layers.0.linear_attn.in_proj_b",
+      "model.language_model.layers.0.linear_attn.in_proj_qkv",
+      "model.language_model.layers.0.linear_attn.in_proj_z",
+      "model.language_model.layers.0.linear_attn.out_proj",
+      "model.language_model.layers.0.mlp.gate",
+      "model.language_model.layers.0.mlp.shared_expert.down_proj",
+      "model.language_model.layers.0.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.0.mlp.shared_expert.up_proj",
+      "model.language_model.layers.0.mlp.shared_expert_gate",
+      "model.language_model.layers.0.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.1.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.1.linear_attn.conv1d",
+      "model.language_model.layers.1.linear_attn.in_proj_a",
+      "model.language_model.layers.1.linear_attn.in_proj_b",
+      "model.language_model.layers.1.linear_attn.in_proj_qkv",
+      "model.language_model.layers.1.linear_attn.in_proj_z",
+      "model.language_model.layers.1.linear_attn.out_proj",
+      "model.language_model.layers.1.mlp.gate",
+      "model.language_model.layers.1.mlp.shared_expert.down_proj",
+      "model.language_model.layers.1.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.1.mlp.shared_expert.up_proj",
+      "model.language_model.layers.1.mlp.shared_expert_gate",
+      "model.language_model.layers.1.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.1.ple.conv1d",
+      "model.language_model.layers.1.ple.key_proj",
+      "model.language_model.layers.1.ple.value_proj",
+      "model.language_model.layers.2.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.2.linear_attn.conv1d",
+      "model.language_model.layers.2.linear_attn.in_proj_a",
+      "model.language_model.layers.2.linear_attn.in_proj_b",
+      "model.language_model.layers.2.linear_attn.in_proj_qkv",
+      "model.language_model.layers.2.linear_attn.in_proj_z",
+      "model.language_model.layers.2.linear_attn.out_proj",
+      "model.language_model.layers.2.mlp.gate",
+      "model.language_model.layers.2.mlp.shared_expert.down_proj",
+      "model.language_model.layers.2.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.2.mlp.shared_expert.up_proj",
+      "model.language_model.layers.2.mlp.shared_expert_gate",
+      "model.language_model.layers.2.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.3.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.3.mlp.gate",
+      "model.language_model.layers.3.mlp.shared_expert.down_proj",
+      "model.language_model.layers.3.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.3.mlp.shared_expert.up_proj",
+      "model.language_model.layers.3.mlp.shared_expert_gate",
+      "model.language_model.layers.3.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.3.self_attn.indexer.index_qk_proj",
+      "model.language_model.layers.3.self_attn.k_proj",
+      "model.language_model.layers.3.self_attn.o_proj",
+      "model.language_model.layers.3.self_attn.q_proj",
+      "model.language_model.layers.3.self_attn.v_proj",
+      "model.language_model.layers.4.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.4.linear_attn.conv1d",
+      "model.language_model.layers.4.linear_attn.in_proj_a",
+      "model.language_model.layers.4.linear_attn.in_proj_b",
+      "model.language_model.layers.4.linear_attn.in_proj_qkv",
+      "model.language_model.layers.4.linear_attn.in_proj_z",
+      "model.language_model.layers.4.linear_attn.out_proj",
+      "model.language_model.layers.4.mlp.gate",
+      "model.language_model.layers.4.mlp.shared_expert.down_proj",
+      "model.language_model.layers.4.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.4.mlp.shared_expert.up_proj",
+      "model.language_model.layers.4.mlp.shared_expert_gate",
+      "model.language_model.layers.4.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.5.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.5.linear_attn.conv1d",
+      "model.language_model.layers.5.linear_attn.in_proj_a",
+      "model.language_model.layers.5.linear_attn.in_proj_b",
+      "model.language_model.layers.5.linear_attn.in_proj_qkv",
+      "model.language_model.layers.5.linear_attn.in_proj_z",
+      "model.language_model.layers.5.linear_attn.out_proj",
+      "model.language_model.layers.5.mlp.gate",
+      "model.language_model.layers.5.mlp.shared_expert.down_proj",
+      "model.language_model.layers.5.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.5.mlp.shared_expert.up_proj",
+      "model.language_model.layers.5.mlp.shared_expert_gate",
+      "model.language_model.layers.5.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.6.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.6.linear_attn.conv1d",
+      "model.language_model.layers.6.linear_attn.in_proj_a",
+      "model.language_model.layers.6.linear_attn.in_proj_b",
+      "model.language_model.layers.6.linear_attn.in_proj_qkv",
+      "model.language_model.layers.6.linear_attn.in_proj_z",
+      "model.language_model.layers.6.linear_attn.out_proj",
+      "model.language_model.layers.6.mlp.gate",
+      "model.language_model.layers.6.mlp.shared_expert.down_proj",
+      "model.language_model.layers.6.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.6.mlp.shared_expert.up_proj",
+      "model.language_model.layers.6.mlp.shared_expert_gate",
+      "model.language_model.layers.6.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.7.attn_hyper_connection.block_inject_weight",
+      "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.7.mlp.gate",
+      "model.language_model.layers.7.mlp.shared_expert.down_proj",
+      "model.language_model.layers.7.mlp.shared_expert.gate_proj",
+      "model.language_model.layers.7.mlp.shared_expert.up_proj",
+      "model.language_model.layers.7.mlp.shared_expert_gate",
+      "model.language_model.layers.7.mlp_hyper_connection.block_inject_weight",
+      "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down",
+      "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up",
+      "model.language_model.layers.7.self_attn.indexer.index_qk_proj",
+      "model.language_model.layers.7.self_attn.k_proj",
+      "model.language_model.layers.7.self_attn.o_proj",
+      "model.language_model.layers.7.self_attn.q_proj",
+      "model.language_model.layers.7.self_attn.v_proj",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.patch_embed.proj",
+      "model.visual.pos_embed",
+      "mtp.fc_embedding",
+      "mtp.fc_hidden",
+      "mtp.hyper_connection_mixer.input_mix_weight_down",
+      "mtp.hyper_connection_mixer.input_mix_weight_up",
+      "mtp.layers.0.attn_hyper_connection.block_inject_weight",
+      "mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
+      "mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
+      "mtp.layers.0.mlp.gate",
+      "mtp.layers.0.mlp.shared_expert.down_proj",
+      "mtp.layers.0.mlp.shared_expert.gate_proj",
+      "mtp.layers.0.mlp.shared_expert.up_proj",
+      "mtp.layers.0.mlp.shared_expert_gate",
+      "mtp.layers.0.mlp_hyper_connection.block_inject_weight",
+      "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
+      "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
+      "mtp.layers.0.self_attn.indexer.index_qk_proj",
+      "mtp.layers.0.self_attn.k_proj",
+      "mtp.layers.0.self_attn.o_proj",
+      "mtp.layers.0.self_attn.q_proj",
+      "mtp.layers.0.self_attn.v_proj"
+    ],
+    "modules_to_convert": [
+      "ple.ple_embedding.ngram_embedding"
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be8d3a864c25cdf7c6dc7cdca2f45b34f20e52a6fd316be66a09b9d5bba620b
+size 37655018

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"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
+size 12809320

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "additional_special_tokens": [
+        "<|im_start|>",
+        "<|im_end|>",
+        "<|object_ref_start|>",
+        "<|object_ref_end|>",
+        "<|box_start|>",
+        "<|box_end|>",
+        "<|quad_start|>",
+        "<|quad_end|>",
+        "<|vision_start|>",
+        "<|vision_end|>",
+        "<|vision_pad|>",
+        "<|image_pad|>",
+        "<|video_pad|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n    {%- endif %}\n    {%- if resolved_reasoning_effort == 'xhigh' %}\n        {%- 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.' %}\n    {%- elif resolved_reasoning_effort == 'low' %}\n        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n    {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if reasoning_instructions %}\n        {{- reasoning_instructions + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\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>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '')  + content + '<|im_end|>\\n' }}\n        {%- elif reasoning_instructions %}\n            {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- elif reasoning_instructions %}\n        {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "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+",
+    "extra_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|>"
+    }
+}

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"
+}