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

.meta.json

@@ -0,0 +1,4 @@
+{
+  "torch": "2.11.0",
+  "transformers": "5.5.0"
+}

README.md

@@ -0,0 +1,303 @@
+---
+library_name: transformers
+base_model:
+- Qwen/Qwen3.6-27B
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B).
+
+| File path | Size |
+|------|------|
+| model.safetensors | 8.8MB |
+
+
+### Example usage:
+
+- vLLM
+
+```bash
+# Multi-token prediction is supported
+model_id=tiny-random/qwen3.6
+vllm serve $model_id \
+     --tensor-parallel-size 2 \
+     --speculative-config.method qwen3_next_mtp \
+     --speculative-config.num_speculative_tokens 2 \
+     --reasoning-parser qwen3 \
+     --tool-call-parser qwen3_coder \
+     --enable-auto-tool-choice \
+     --max-cudagraph-capture-size 16
+```
+
+- SGLang
+
+```bash
+# Multi-token prediction is supported
+model_id=tiny-random/qwen3.6
+python3 -m sglang.launch_server \
+  --model-path $model_id \
+  --tp-size 2 \
+  --tool-call-parser qwen3_coder  \
+  --reasoning-parser qwen3 \
+  --speculative-algo NEXTN \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4
+```
+
+- Transformers
+
+```python
+import torch
+from transformers import (
+    Qwen3_5ForConditionalGeneration,
+    AutoProcessor,
+)
+
+model_id = "tiny-random/qwen3.6"
+model = Qwen3_5ForConditionalGeneration.from_pretrained(
+    model_id, dtype=torch.bfloat16, device_map="auto",
+)
+processor = AutoProcessor.from_pretrained(model_id)
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"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)
+
+generated_ids = model.generate(**inputs, max_new_tokens=32)
+output_text = processor.batch_decode(generated_ids[0], skip_special_tokens=False)[0]
+print(output_text.replace('<|image_pad|>', "I"))
+```
+
+### Codes to create this repo:
+
+<details>
+<summary>Click to expand</summary>
+
+```python
+import json
+from copy import deepcopy
+from pathlib import Path
+
+import torch
+from huggingface_hub import file_exists, hf_hub_download
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoProcessor,
+    GenerationConfig,
+    Qwen3_5ForConditionalGeneration,
+    set_seed,
+)
+
+source_model_id = "Qwen/Qwen3.6-27B"
+save_folder = "/tmp/tiny-random/qwen36"
+
+processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
+processor.save_pretrained(save_folder)
+
+with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
+    config_json = json.load(f)
+
+config_json['text_config'].update({
+    'head_dim': 32,
+    'hidden_size': 8,
+    "layer_types": ['linear_attention'] * 3 + ['full_attention'],
+    'intermediate_size': 32,
+    'num_hidden_layers': 4,
+    'num_attention_heads': 8,
+    'num_key_value_heads': 4,
+    "linear_key_head_dim": 32,
+    "linear_num_key_heads": 4,
+    "linear_num_value_heads": 8,
+    "linear_value_head_dim": 32,
+})
+config_json['text_config']['rope_parameters']['mrope_section'] = [1, 1, 2]
+config_json["tie_word_embeddings"] = False
+config_json['vision_config'].update(
+    {
+        'hidden_size': 64,
+        'intermediate_size': 128,
+        'num_heads': 2,
+        'out_hidden_size': 8,
+        'depth': 2,
+    }
+)
+with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
+    json.dump(config_json, f, indent=2)
+
+config = AutoConfig.from_pretrained(
+    save_folder,
+    trust_remote_code=True,
+)
+print(config)
+set_seed(42)
+torch.set_default_dtype(torch.bfloat16)
+model = Qwen3_5ForConditionalGeneration(config)
+# in Qwen/Qwen3.6-27B release, all tensors are in bfloat16
+# with torch.no_grad():
+#     for i in range(3):
+#         attn = model.model.language_model.layers[i].linear_attn
+#         attn.A_log = torch.nn.Parameter(attn.A_log.float())
+#         attn.norm.float()
+
+print(model.state_dict()['model.language_model.layers.0.linear_attn.A_log'].dtype)
+print(model.state_dict()['model.language_model.layers.0.linear_attn.norm.weight'].dtype)
+
+model.mtp = torch.nn.ModuleDict({
+    "pre_fc_norm_embedding": torch.nn.RMSNorm(config.text_config.hidden_size),
+    "fc": torch.nn.Linear(config.text_config.hidden_size * 2, config.text_config.hidden_size, bias=False),
+    "layers": torch.nn.ModuleList([deepcopy(model.model.language_model.layers[3])]),
+    "norm": torch.nn.RMSNorm(config.text_config.hidden_size),
+    "pre_fc_norm_hidden": torch.nn.RMSNorm(config.text_config.hidden_size),
+})
+torch.set_default_dtype(torch.float32)
+if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
+    model.generation_config = GenerationConfig.from_pretrained(
+        source_model_id, trust_remote_code=True,
+    )
+    model.generation_config.do_sample = True
+    print(model.generation_config)
+model = model.cpu()
+set_seed(42)
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.2)
+        print(name, p.shape)
+model.save_pretrained(save_folder)
+```
+
+</details>
+
+### Printing the model:
+
+<details><summary>Click to expand</summary>
+
+```text
+Qwen3_5ForConditionalGeneration(
+  (model): Qwen3_5Model(
+    (visual): Qwen3_5VisionModel(
+      (patch_embed): Qwen3_5VisionPatchEmbed(
+        (proj): Conv3d(3, 64, kernel_size=(2, 16, 16), stride=(2, 16, 16))
+      )
+      (pos_embed): Embedding(2304, 64)
+      (rotary_pos_emb): Qwen3_5VisionRotaryEmbedding()
+      (blocks): ModuleList(
+        (0-1): 2 x Qwen3_5VisionBlock(
+          (norm1): LayerNorm((64,), eps=1e-06, elementwise_affine=True)
+          (norm2): LayerNorm((64,), eps=1e-06, elementwise_affine=True)
+          (attn): Qwen3_5VisionAttention(
+            (qkv): Linear(in_features=64, out_features=192, bias=True)
+            (proj): Linear(in_features=64, out_features=64, bias=True)
+          )
+          (mlp): Qwen3_5VisionMLP(
+            (linear_fc1): Linear(in_features=64, out_features=128, bias=True)
+            (linear_fc2): Linear(in_features=128, out_features=64, bias=True)
+            (act_fn): GELUTanh()
+          )
+        )
+      )
+      (merger): Qwen3_5VisionPatchMerger(
+        (norm): LayerNorm((64,), eps=1e-06, elementwise_affine=True)
+        (linear_fc1): Linear(in_features=256, out_features=256, bias=True)
+        (act_fn): GELU(approximate='none')
+        (linear_fc2): Linear(in_features=256, out_features=8, bias=True)
+      )
+    )
+    (language_model): Qwen3_5TextModel(
+      (embed_tokens): Embedding(248320, 8)
+      (layers): ModuleList(
+        (0-2): 3 x Qwen3_5DecoderLayer(
+          (linear_attn): Qwen3_5GatedDeltaNet(
+            (act): SiLUActivation()
+            (conv1d): Conv1d(512, 512, kernel_size=(4,), stride=(1,), padding=(3,), groups=512, bias=False)
+            (norm): Qwen3_5RMSNormGated()
+            (out_proj): Linear(in_features=256, out_features=8, bias=False)
+            (in_proj_qkv): Linear(in_features=8, out_features=512, bias=False)
+            (in_proj_z): Linear(in_features=8, out_features=256, bias=False)
+            (in_proj_b): Linear(in_features=8, out_features=8, bias=False)
+            (in_proj_a): Linear(in_features=8, out_features=8, bias=False)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=8, out_features=32, bias=False)
+            (up_proj): Linear(in_features=8, out_features=32, bias=False)
+            (down_proj): Linear(in_features=32, out_features=8, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((8,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((8,), eps=1e-06)
+        )
+        (3): Qwen3_5DecoderLayer(
+          (self_attn): Qwen3_5Attention(
+            (q_proj): Linear(in_features=8, out_features=512, bias=False)
+            (k_proj): Linear(in_features=8, out_features=128, bias=False)
+            (v_proj): Linear(in_features=8, out_features=128, bias=False)
+            (o_proj): Linear(in_features=256, out_features=8, bias=False)
+            (q_norm): Qwen3_5RMSNorm((32,), eps=1e-06)
+            (k_norm): Qwen3_5RMSNorm((32,), eps=1e-06)
+          )
+          (mlp): Qwen3_5MLP(
+            (gate_proj): Linear(in_features=8, out_features=32, bias=False)
+            (up_proj): Linear(in_features=8, out_features=32, bias=False)
+            (down_proj): Linear(in_features=32, out_features=8, bias=False)
+            (act_fn): SiLUActivation()
+          )
+          (input_layernorm): Qwen3_5RMSNorm((8,), eps=1e-06)
+          (post_attention_layernorm): Qwen3_5RMSNorm((8,), eps=1e-06)
+        )
+      )
+      (norm): Qwen3_5RMSNorm((8,), eps=1e-06)
+      (rotary_emb): Qwen3_5TextRotaryEmbedding()
+    )
+  )
+  (lm_head): Linear(in_features=8, out_features=248320, bias=False)
+  (mtp): ModuleDict(
+    (pre_fc_norm_embedding): RMSNorm((8,), eps=None, elementwise_affine=True)
+    (fc): Linear(in_features=16, out_features=8, bias=False)
+    (layers): ModuleList(
+      (0): Qwen3_5DecoderLayer(
+        (self_attn): Qwen3_5Attention(
+          (q_proj): Linear(in_features=8, out_features=512, bias=False)
+          (k_proj): Linear(in_features=8, out_features=128, bias=False)
+          (v_proj): Linear(in_features=8, out_features=128, bias=False)
+          (o_proj): Linear(in_features=256, out_features=8, bias=False)
+          (q_norm): Qwen3_5RMSNorm((32,), eps=1e-06)
+          (k_norm): Qwen3_5RMSNorm((32,), eps=1e-06)
+        )
+        (mlp): Qwen3_5MLP(
+          (gate_proj): Linear(in_features=8, out_features=32, bias=False)
+          (up_proj): Linear(in_features=8, out_features=32, bias=False)
+          (down_proj): Linear(in_features=32, out_features=8, bias=False)
+          (act_fn): SiLUActivation()
+        )
+        (input_layernorm): Qwen3_5RMSNorm((8,), eps=1e-06)
+        (post_attention_layernorm): Qwen3_5RMSNorm((8,), eps=1e-06)
+      )
+    )
+    (norm): RMSNorm((8,), eps=None, elementwise_affine=True)
+    (pre_fc_norm_hidden): RMSNorm((8,), eps=None, elementwise_affine=True)
+  )
+)
+```
+
+</details>
+
+### Test environment:
+
+- torch: 2.11.0
+- transformers: 5.5.0

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "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": 32,
+    "hidden_act": "silu",
+    "hidden_size": 8,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_types": [
+      "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": 8,
+    "linear_value_head_dim": 32,
+    "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": 8,
+    "num_hidden_layers": 4,
+    "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": [
+        1,
+        1,
+        2
+      ],
+      "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": "5.5.0",
+  "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": "qwen3_5",
+    "num_heads": 2,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 8,
+    "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 +1,14 @@
+{
+  "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": "5.5.0",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5924d21a84d7a69fe511f87ab99bed3ffb7e4dabfe4ad9e567cde7786e93a7
+size 8825216

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"
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}