Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,254 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+inference: true
+widget:
+  - text: Hello!
+    example_title: Hello world
+    group: Python
+base_model:
+- Qwen/Qwen3-Next-80B-A3B-Instruct
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [Qwen/Qwen3-Next-80B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct).
+
+### Example usage:
+
+- vLLM
+
+```bash
+ VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
+    vllm serve tiny-random/qwen3-next-moe \
+    --tensor-parallel-size 4 \
+    --max-model-len 262144 \
+    --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
+
+```
+
+- SGLang
+
+```bash
+SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 \
+python -m sglang.launch_server \
+    --model-path tiny-random/qwen3-next-moe \
+    --tp-size 4 --context-length 262144 \
+    --mem-fraction-static 0.8 \
+    --speculative-algo NEXTN \
+    --speculative-num-steps 3 \
+    --speculative-eagle-topk 1 \
+    --speculative-num-draft-tokens 4
+
+```
+
+- Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+model_id = "tiny-random/qwen3-next-moe"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    dtype="auto",
+    device_map="cuda",
+)
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt},
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=8,
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+print("content:", content)
+```
+
+### Codes to create this repo:
+
+```python
+from copy import deepcopy
+
+import torch
+import torch.nn as nn
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    GenerationConfig,
+    pipeline,
+    set_seed,
+)
+
+source_model_id = "Qwen/Qwen3-Next-80B-A3B-Instruct"
+save_folder = "/tmp/tiny-random/qwen3-next-moe"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+tokenizer.save_pretrained(save_folder)
+
+config = AutoConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+config._name_or_path = source_model_id
+config.hidden_size = 8
+config.intermediate_size = 32
+config.head_dim = 32
+config.num_key_value_heads = 8
+config.num_attention_heads = 16
+config.num_hidden_layers = 4
+config.tie_word_embeddings = False
+config.linear_num_key_heads = 8
+config.linear_num_value_heads = 16
+config.moe_intermediate_size = 32
+config.num_experts = 32
+config.num_experts_per_tok = 10
+config.layer_types = config.layer_types[:4]
+config.shared_expert_intermediate_size = 32
+model = AutoModelForCausalLM.from_config(
+    config,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+)
+model.generation_config = GenerationConfig.from_pretrained(
+    source_model_id, trust_remote_code=True,
+)
+# MTP
+model.mtp = nn.ModuleDict({
+    "pre_fc_norm_embedding": nn.RMSNorm(config.hidden_size),
+    "fc": nn.Linear(config.hidden_size * 2, config.hidden_size, bias=False),
+    "norm": nn.RMSNorm(config.hidden_size),
+    "pre_fc_norm_hidden": nn.RMSNorm(config.hidden_size),
+    "layers": nn.ModuleList([deepcopy(model.model.layers[3])]),
+})
+set_seed(42)
+with torch.no_grad():
+    for name, p in sorted(model.named_parameters()):
+        torch.nn.init.normal_(p, 0, 0.1)
+        print(name, p.shape)
+model.save_pretrained(save_folder)
+```
+
+### Printing the model:
+
+```text
+Qwen3NextForCausalLM(
+  (model): Qwen3NextModel(
+    (embed_tokens): Embedding(151936, 8)
+    (layers): ModuleList(
+      (0-2): 3 x Qwen3NextDecoderLayer(
+        (linear_attn): Qwen3NextGatedDeltaNet(
+          (act): SiLU()
+          (conv1d): Conv1d(4096, 4096, kernel_size=(4,), stride=(1,), padding=(3,), groups=4096, bias=False)
+          (in_proj_qkvz): Linear(in_features=8, out_features=6144, bias=False)
+          (in_proj_ba): Linear(in_features=8, out_features=32, bias=False)
+          (norm): FusedRMSNormGated(128, eps=1e-06, activation=silu)
+          (out_proj): Linear(in_features=2048, out_features=8, bias=False)
+        )
+        (mlp): Qwen3NextSparseMoeBlock(
+          (gate): Linear(in_features=8, out_features=32, bias=False)
+          (experts): ModuleList(
+            (0-31): 32 x Qwen3NextMLP(
+              (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): SiLU()
+            )
+          )
+          (shared_expert): Qwen3NextMLP(
+            (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): SiLU()
+          )
+          (shared_expert_gate): Linear(in_features=8, out_features=1, bias=False)
+        )
+        (input_layernorm): Qwen3NextRMSNorm((8,), eps=1e-06)
+        (post_attention_layernorm): Qwen3NextRMSNorm((8,), eps=1e-06)
+      )
+      (3): Qwen3NextDecoderLayer(
+        (self_attn): Qwen3NextAttention(
+          (q_proj): Linear(in_features=8, out_features=1024, bias=False)
+          (k_proj): Linear(in_features=8, out_features=256, bias=False)
+          (v_proj): Linear(in_features=8, out_features=256, bias=False)
+          (o_proj): Linear(in_features=512, out_features=8, bias=False)
+          (q_norm): Qwen3NextRMSNorm((32,), eps=1e-06)
+          (k_norm): Qwen3NextRMSNorm((32,), eps=1e-06)
+        )
+        (mlp): Qwen3NextSparseMoeBlock(
+          (gate): Linear(in_features=8, out_features=32, bias=False)
+          (experts): ModuleList(
+            (0-31): 32 x Qwen3NextMLP(
+              (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): SiLU()
+            )
+          )
+          (shared_expert): Qwen3NextMLP(
+            (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): SiLU()
+          )
+          (shared_expert_gate): Linear(in_features=8, out_features=1, bias=False)
+        )
+        (input_layernorm): Qwen3NextRMSNorm((8,), eps=1e-06)
+        (post_attention_layernorm): Qwen3NextRMSNorm((8,), eps=1e-06)
+      )
+    )
+    (norm): Qwen3NextRMSNorm((8,), eps=1e-06)
+    (rotary_emb): Qwen3NextRotaryEmbedding()
+  )
+  (lm_head): Linear(in_features=8, out_features=151936, 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)
+    (norm): RMSNorm((8,), eps=None, elementwise_affine=True)
+    (pre_fc_norm_hidden): RMSNorm((8,), eps=None, elementwise_affine=True)
+    (layers): ModuleList(
+      (0): Qwen3NextDecoderLayer(
+        (self_attn): Qwen3NextAttention(
+          (q_proj): Linear(in_features=8, out_features=1024, bias=False)
+          (k_proj): Linear(in_features=8, out_features=256, bias=False)
+          (v_proj): Linear(in_features=8, out_features=256, bias=False)
+          (o_proj): Linear(in_features=512, out_features=8, bias=False)
+          (q_norm): Qwen3NextRMSNorm((32,), eps=1e-06)
+          (k_norm): Qwen3NextRMSNorm((32,), eps=1e-06)
+        )
+        (mlp): Qwen3NextSparseMoeBlock(
+          (gate): Linear(in_features=8, out_features=32, bias=False)
+          (experts): ModuleList(
+            (0-31): 32 x Qwen3NextMLP(
+              (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): SiLU()
+            )
+          )
+          (shared_expert): Qwen3NextMLP(
+            (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): SiLU()
+          )
+          (shared_expert_gate): Linear(in_features=8, out_features=1, bias=False)
+        )
+        (input_layernorm): Qwen3NextRMSNorm((8,), eps=1e-06)
+        (post_attention_layernorm): Qwen3NextRMSNorm((8,), eps=1e-06)
+      )
+    )
+  )
+)
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|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 %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "Qwen3NextForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "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": 128,
+  "linear_num_key_heads": 8,
+  "linear_num_value_heads": 16,
+  "linear_value_head_dim": 128,
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_next",
+  "moe_intermediate_size": 32,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 32,
+  "num_experts_per_tok": 10,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 32,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.0.dev0",
+  "trust_remote_code": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4378d59f21cb212c6ca10786e64c4bea327f62dbfc93b2f42c83962a80912b
+size 5740672

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}