Duplicate from huihui-ai/Huihui-Qwen3-Coder-Next-abliterated

Co-authored-by: huihui.ai <huihui-ai@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,241 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3-Coder-Next
+tags:
+- abliterated
+- uncensored
+---
+
+# huihui-ai/Huihui-Qwen3-Coder-Next-abliterated
+
+
+This is an uncensored version of [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
+This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
+
+## ollama
+
+Please use the latest version of [ollama 0.15.5](https://github.com/ollama/ollama/releases/tag/v0.15.5)
+
+You can use [huihui_ai/qwen3-coder-next-abliterated](https://ollama.com/huihui_ai/qwen3-coder-next-abliterated) directly, 
+```
+ollama run huihui_ai/qwen3-coder-next-abliterated
+```
+
+## chat_template-vl.jinja
+
+We have added a new file named [chat_template-vl.jinja](https://huggingface.co/huihui-ai/Huihui-Qwen3-Coder-Next-abliterated/blob/main/chat_template-vl.jinja), which comes from the path `huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated`. 
+
+The new file chat_template-vl.jinja is more compatible with using Tool Calling in [llama-server](https://github.com/ggml-org/llama.cpp/releases/tag/b7952), 
+especially when [opencode](https://github.com/anomalyco/opencode/releases/tag/v1.1.53) is involved.
+
+
+## Usage
+You can use this model in your applications by loading it with Hugging Face's `transformers` library:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig
+import torch
+import os
+import signal
+import random
+import numpy as np
+import time
+import sys
+
+if (
+    "PYTORCH_ALLOC_CONF" not in os.environ
+    and "PYTORCH_CUDA_ALLOC_CONF" not in os.environ
+):
+    print(f"PYTORCH_ALLOC_CONF.")
+    os.environ["PYTORCH_ALLOC_CONF"] = "expandable_segments:True"
+
+cpu_count = os.cpu_count()
+print(f"Number of CPU cores in the system: {cpu_count}")
+half_cpu_count = cpu_count // 2
+os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
+os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
+torch.set_num_threads(half_cpu_count)
+
+print(f"PyTorch threads: {torch.get_num_threads()}")
+print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
+print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")
+
+# Load the model and tokenizer
+MODEL_ID = "huihui-ai/Huihui-Qwen3-Coder-Next-abliterated"
+
+print(f"Load Model {MODEL_ID} ... ")
+quant_config_4 = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=True,
+    llm_int8_enable_fp32_cpu_offload=True,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    device_map="auto",
+    trust_remote_code=True,
+    torch_dtype="auto",
+    low_cpu_mem_usage=True,
+    quantization_config=quant_config_4,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
+
+messages = []
+skip_prompt=True
+skip_special_tokens=True
+
+class CustomTextStreamer(TextStreamer):
+    def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
+        super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
+        self.generated_text = ""
+        self.stop_flag = False
+        self.init_time = time.time()  # Record initialization time
+        self.end_time = None  # To store end time
+        self.first_token_time = None  # To store first token generation time
+        self.token_count = 0  # To track total tokens
+
+    def on_finalized_text(self, text: str, stream_end: bool = False):
+        if self.first_token_time is None and text.strip():  # Set first token time on first non-empty text
+            self.first_token_time = time.time()
+        self.generated_text += text
+
+        self.token_count += 1
+
+        print(text, end="", flush=True)
+        if stream_end:
+            self.end_time = time.time()  # Record end time when streaming ends
+        if self.stop_flag:
+            raise StopIteration
+
+    def stop_generation(self):
+        self.stop_flag = True
+        self.end_time = time.time()  # Record end time when generation is stopped
+
+    def get_metrics(self):
+        """Returns initialization time, first token time, first token latency, end time, total time, total tokens, and tokens per second."""
+        if self.end_time is None:
+            self.end_time = time.time()  # Set end time if not already set
+        total_time = self.end_time - self.init_time  # Total time from init to end
+        tokens_per_second = self.token_count / total_time if total_time > 0 else 0
+        first_token_latency = (self.first_token_time - self.init_time) if self.first_token_time is not None else None
+        metrics = {
+            "init_time": self.init_time,
+            "first_token_time": self.first_token_time,
+            "first_token_latency": first_token_latency,
+            "end_time": self.end_time,
+            "total_time": total_time,  # Total time in seconds
+            "total_tokens": self.token_count,
+            "tokens_per_second": tokens_per_second
+        }
+        return metrics
+
+def generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, max_new_tokens):
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+    model_inputs = tokenizer(
+        [text],
+        return_tensors="pt",
+    ).to(model.device)
+
+    streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
+
+    def signal_handler(sig, frame):
+        streamer.stop_generation()
+        print("\n[Generation stopped by user with Ctrl+C]")
+
+    signal.signal(signal.SIGINT, signal_handler)
+
+    print("Response: ", end="", flush=True)
+    try:
+        generated_ids = model.generate(
+            **model_inputs,
+            max_new_tokens = max_new_tokens,
+            streamer=streamer,
+        )
+        del generated_ids
+    except StopIteration:
+        print("\n[Stopped by user]")
+
+    del model_inputs
+    torch.cuda.empty_cache()
+    signal.signal(signal.SIGINT, signal.SIG_DFL)
+
+    return streamer.generated_text, streamer.stop_flag, streamer.get_metrics()
+
+
+while True:
+    print(f"skip_prompt: {skip_prompt}")
+    print(f"skip_special_tokens: {skip_special_tokens}")
+
+    user_input = input("User: ").strip()
+    if user_input.lower() == "/exit":
+        print("Exiting chat.")
+        break
+    if user_input.lower() == "/clear":
+        messages = []
+        print("Chat history cleared. Starting a new conversation.")
+        continue
+    if user_input.lower() == "/skip_prompt":
+        skip_prompt = not skip_prompt
+        continue
+    if user_input.lower() == "/skip_special_tokens":
+        skip_special_tokens = not skip_special_tokens
+        continue
+    if not user_input:
+        print("Input cannot be empty. Please enter something.")
+        continue
+
+
+    messages.append({
+        "role": "user",
+        "content": user_input
+    })
+
+    response, stop_flag, metrics = generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, 40960)
+    print("\n\nMetrics:")
+    for key, value in metrics.items():
+        print(f"  {key}: {value}")
+
+
+    print("", flush=True)
+    if stop_flag:
+        continue
+    messages.append({
+        "role": "assistant",
+        "content": response.strip()
+    })
+```
+
+### Usage Warnings
+
+
+ - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
+
+ - **Not Suitable for All Audiences**: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
+
+ - **Legal and Ethical Responsibilities**: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
+
+ - **Research and Experimental Use**: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
+
+ - **Monitoring and Review Recommendations**: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
+
+ - **No Default Safety Guarantees**: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
+
+
+### Donation
+##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
+- bitcoin:
+```
+  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
+```
+- Support our work on [Ko-fi](https://ko-fi.com/huihuiai)!
+

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-vl.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.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' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 %}

chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is string %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {%- set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- 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>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- 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 if args_value is string else args_value | tojson | safe %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,94 @@
+{
+  "architectures": [
+    "Qwen3NextForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_next",
+  "moe_intermediate_size": 512,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 512,
+  "num_experts_per_tok": 10,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 512,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "top_k": 40,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7742dee28eed9b2b6d7c2ba09c39204774cfc6eccf91bdf13f057f6111d592b
+size 5000007128

model-00002-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe43addb17224f42808722bb8b72f1a9ac1e69f35b29db5f350fcd465f97b60
+size 5000242936

model-00003-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325a1b7fd5c207ced92e73878a59f3f7d55e01c62be32cf1d7232e53060a87c5
+size 5000253712

model-00004-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7159d0a65ae2d5cc19eaae354466d0afceee28419581de374d23ff698c8bdeaf
+size 5000242936

model-00005-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2c5363db8a86bd98c53d0c9760b80924de3b1fea2e58f1ff27441baf7b82c2
+size 5000253760

model-00006-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50aeda421ae42201207d469a039cfe53dc89d74947e69906dd6c5d5031b58d0a
+size 5000242936

model-00007-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfbc0dd9dcd77151b1e071531fc56f1999ad8c4f29148180e4f0ef971368160
+size 4998483600

model-00008-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99f4913b603c09cad6a4513432c94fe0ea69fa9d38f1dd2344bac61ba757b77
+size 4999918888

model-00009-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e1dc03ff11037805d8c53ef61fd5d562c785d29e6742830a0713b6021c51c9
+size 4998485240

model-00010-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb17978fcc800b9f8e72b35b3171570f39f698f9c57d13a51f165fc37ba7735
+size 5000245296

model-00011-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316d96cd9cd636957ef089bc6dd307a660f838c5f0b6cc830e53d64ccda5d0a0
+size 5000256048

model-00012-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb1116c58f883f27c97c8f77166531239c21a86d148ae18a539844b8e8ba277
+size 4998485520

model-00013-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306f572e66da8ed5401794956b98d157b38ac86df958dca462f56780163f2808
+size 4999918568

model-00014-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b271e8c1eeb25e48d0a91c412c21e87b890d7842fec401a78acd90097b49cc3
+size 4998485432

model-00015-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02fef45ca8a8a2e181364bed47b02d2cafd371de72447d774b38c7182ee1aeb
+size 5000245056

model-00016-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa396498c606cb1af64a04624a73390aef58e10d15682f1c05fa8030a9bcdd6
+size 5000256248

model-00017-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9332eb2604728f1800c41da5d7348f5ac3c8b2e6d11c6673504adb76de2d7e16
+size 5000245120

model-00018-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3ad2214399a40205b16f29398955e470d09bed031527ebd97ffc371086a007
+size 5000256184

model-00019-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6deeecc53230f7b68036cedb2bd08ea3fb8a9cf4652bd24c2a106f41e7044add
+size 5000245176

model-00020-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a261627efcba2d1b4834a4a60f5e388060d672ae7e0419979d10753bcdc60c
+size 4998485264

model-00021-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7d836f9972b563d47c0c18368421140f0a6d2ec716eac2d7b451f5ef94d07c
+size 4999918824

model-00022-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46785a76c70cce79eef743d78def866e9c3efe55718e6e8abedbcf4734810aed
+size 4998485208

model-00023-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e0b19eda5c994984d2fc5c7e339f917be776c3aa79e0842098d1795ce16622
+size 5000245288

model-00024-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3d17a18ed4d8e059faa97c7a39f897d3b9db24fb1bf8b8ced2da18a91a59b9
+size 5000256056

model-00025-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc6d28db22d1096c293c6f8d1c3353b0ebe9cb2e2fcc33a06e76dfe4edda2fc
+size 5000245296

model-00026-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc851b1a94b5a65510ce42956827f6c8b2001c494bbde6047a44bc7a0aaadf0
+size 5000256104

model-00027-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2e38993c8398dbc885e859be96986520659e671f06b0a43b5727a04c2e22ec
+size 5000245296

model-00028-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f83450cab3992e05421532b1c2d5f32afa4047e50068baa529c21cb0d2e086f
+size 4998485240

model-00029-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c28c2c9580daed3682a495fa919fac47df3544cb49c2b31c932bce2c56c6a7
+size 4999918888

model-00030-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2d014fe732578e969d131c7f91d8e75813f7624ba9364e423caa7e824c00db
+size 4998485240

model-00031-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc238ec36871ba09006dc3ae607ab4c91a62d3a642d2f5b9d13e2b1192202477
+size 5000245296

model-00032-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853be074450c496d8434fda9043d5d1d28964d6ce498583ce3a0990719a50917
+size 4365997256

qwen3_coder_detector_sgl.py

@@ -0,0 +1,474 @@
+import ast
+import json
+import logging
+import re
+from typing import Any, List, Optional
+
+from sglang.srt.entrypoints.openai.protocol import Tool
+from sglang.srt.function_call.base_format_detector import BaseFormatDetector
+from sglang.srt.function_call.core_types import (
+    StreamingParseResult,
+    ToolCallItem,
+    _GetInfoFunc,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class Qwen3CoderDetector(BaseFormatDetector):
+    def __init__(self):
+        super().__init__()
+
+        # Sentinel tokens
+        self.tool_call_start_token: str = "<tool_call>"
+        self.tool_call_end_token: str = "</tool_call>"
+        self.tool_call_prefix: str = "<function="
+        self.function_end_token: str = "</function>"
+        self.parameter_prefix: str = "<parameter="
+        self.parameter_end_token: str = "</parameter>"
+
+        # Regex for non-streaming fallback
+        self.tool_call_regex = re.compile(r"<tool_call>(.*?)</tool_call>", re.DOTALL)
+        self.tool_call_function_regex = re.compile(
+            r"<function=(.*?)</function>|<function=(.*)$", re.DOTALL
+        )
+        self.tool_call_parameter_regex = re.compile(
+            r"<parameter=(.*?)(?:</parameter>|(?=<parameter=)|(?=</function>)|$)",
+            re.DOTALL,
+        )
+
+        # Streaming State
+        # Base class already initializes _buffer, we just use it directly
+        # No need to check with hasattr - we control the lifecycle through inheritance
+
+        # Index pointing to the next character to be processed in buffer
+        self.parsed_pos: int = 0
+        # Parameter count inside the current tool being processed, used to determine whether to add comma
+        self.current_tool_param_count: int = 0
+        # Flag indicating whether current tool has already sent '{'
+        self.json_started: bool = False
+
+        # [FIX] New state flag: mark whether inside tool_call structure block
+        self.is_inside_tool_call: bool = False
+
+        # Initialize attributes that were missing in the original PR
+        self.current_func_name: Optional[str] = None
+
+    def has_tool_call(self, text: str) -> bool:
+        return self.tool_call_start_token in text
+
+    def _get_arguments_config(
+        self, func_name: str, tools: Optional[list[Tool]]
+    ) -> dict:
+        """Extract argument configuration for a function."""
+        if tools is None:
+            return {}
+        for config in tools:
+            try:
+                config_type = config.type
+                config_function = config.function
+                config_function_name = config_function.name
+            except AttributeError:
+                continue
+
+            if config_type == "function" and config_function_name == func_name:
+                try:
+                    params = config_function.parameters
+                except AttributeError:
+                    return {}
+
+                if isinstance(params, dict) and "properties" in params:
+                    return params["properties"]
+                elif isinstance(params, dict):
+                    return params
+                else:
+                    return {}
+        logger.warning(f"Tool '{func_name}' is not defined in the tools list.")
+        return {}
+
+    def _convert_param_value(
+        self, param_value: str, param_name: str, param_config: dict, func_name: str
+    ) -> Any:
+        """Convert parameter value based on its type in the schema."""
+        # Handle null value for any type
+        if param_value.lower() == "null":
+            return None
+
+        if param_name not in param_config:
+            if param_config != {}:
+                logger.warning(
+                    f"Parsed parameter '{param_name}' is not defined in the tool "
+                    f"parameters for tool '{func_name}', directly returning the string value."
+                )
+            return param_value
+
+        if (
+            isinstance(param_config[param_name], dict)
+            and "type" in param_config[param_name]
+        ):
+            param_type = str(param_config[param_name]["type"]).strip().lower()
+        else:
+            param_type = "string"
+        if param_type in ["string", "str", "text", "varchar", "char", "enum"]:
+            return param_value
+        elif (
+            param_type.startswith("int")
+            or param_type.startswith("uint")
+            or param_type.startswith("long")
+            or param_type.startswith("short")
+            or param_type.startswith("unsigned")
+        ):
+            try:
+                param_value = int(param_value)
+            except Exception:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' is not an integer in tool "
+                    f"'{func_name}', degenerating to string."
+                )
+            return param_value
+        elif param_type.startswith("num") or param_type.startswith("float"):
+            try:
+                maybe_convert = (
+                    False if "." in param_value or "e" in param_value.lower() else True
+                )
+                param_value: float = float(param_value)
+                if maybe_convert and param_value.is_integer():
+                    param_value = int(param_value)
+            except Exception:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a float in tool "
+                    f"'{func_name}', degenerating to string."
+                )
+            return param_value
+        elif param_type in ["boolean", "bool", "binary"]:
+            param_value = param_value.lower()
+            if param_value not in ["true", "false"]:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a boolean (`true` of `false`) in tool '{func_name}', degenerating to false."
+                )
+            return param_value == "true"
+        else:
+            if (
+                param_type in ["object", "array", "arr"]
+                or param_type.startswith("dict")
+                or param_type.startswith("list")
+            ):
+                try:
+                    param_value = json.loads(param_value)
+                    return param_value
+                except Exception:
+                    logger.warning(
+                        f"Parsed value '{param_value}' of parameter '{param_name}' cannot be parsed with json.loads in tool "
+                        f"'{func_name}', will try other methods to parse it."
+                    )
+            try:
+                param_value = ast.literal_eval(param_value)  # safer
+            except Exception:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' cannot be converted via Python `ast.literal_eval()` in tool '{func_name}', degenerating to string."
+                )
+            return param_value
+
+    def detect_and_parse(self, text: str, tools: List[Tool]) -> StreamingParseResult:
+        """One-shot parsing for non-streaming scenarios."""
+        if self.tool_call_start_token not in text:
+            return StreamingParseResult(normal_text=text)
+
+        calls = []
+        try:
+            # Simple cleanup of the text to find tool calls
+            # Note: This is a simplified regex approach consistent with vLLM
+            raw_tool_calls = self.tool_call_regex.findall(text)
+            if not raw_tool_calls:
+                # Fallback: maybe the whole text is inside the tag or tags are stripped
+                if self.tool_call_prefix in text:
+                    raw_tool_calls = [text]
+
+            tool_idx = 0
+            for tool_content in raw_tool_calls:
+                # Find function calls
+                funcs = self.tool_call_function_regex.findall(tool_content)
+                for func_match in funcs:
+                    func_body = func_match[0] or func_match[1]
+                    if ">" not in func_body:
+                        continue
+
+                    name_end = func_body.index(">")
+                    func_name = func_body[:name_end]
+                    params_str = func_body[name_end + 1 :]
+
+                    param_config = self._get_arguments_config(func_name, tools)
+                    parsed_params = {}
+
+                    for p_match in self.tool_call_parameter_regex.findall(params_str):
+                        if ">" not in p_match:
+                            continue
+                        p_idx = p_match.index(">")
+                        p_name = p_match[:p_idx]
+                        p_val = p_match[p_idx + 1 :]
+                        # Remove prefixing and trailing \n
+                        if p_val.startswith("\n"):
+                            p_val = p_val[1:]
+                        if p_val.endswith("\n"):
+                            p_val = p_val[:-1]
+
+                        parsed_params[p_name] = self._convert_param_value(
+                            p_val, p_name, param_config, func_name
+                        )
+
+                    calls.append(
+                        ToolCallItem(
+                            tool_index=tool_idx,
+                            name=func_name,
+                            parameters=json.dumps(parsed_params, ensure_ascii=False),
+                        )
+                    )
+                    tool_idx += 1
+
+            # Determine normal text (text before the first tool call)
+            start_idx = text.find(self.tool_call_start_token)
+            if start_idx == -1:
+                start_idx = text.find(self.tool_call_prefix)
+            normal_text = text[:start_idx] if start_idx > 0 else ""
+
+            return StreamingParseResult(normal_text=normal_text, calls=calls)
+
+        except Exception as e:
+            logger.error(f"Error in detect_and_parse: {e}")
+            return StreamingParseResult(normal_text=text)
+
+    def parse_streaming_increment(
+        self, new_text: str, tools: List[Tool]
+    ) -> StreamingParseResult:
+        """
+        Robust cursor-based streaming parser.
+        """
+        self._buffer += new_text
+
+        # Guard against empty buffer
+        if not self._buffer:
+            return StreamingParseResult()
+
+        calls = []
+        normal_text_chunks = []
+
+        while True:
+            # Working text slice
+            current_slice = self._buffer[self.parsed_pos :]
+
+            # Optimization: If almost empty, wait for more
+            if not current_slice:
+                break
+
+            # -------------------------------------------------------
+            # 1. Priority detection: check if it's the start of Tool Call
+            # -------------------------------------------------------
+            if current_slice.startswith(self.tool_call_start_token):
+                self.parsed_pos += len(self.tool_call_start_token)
+                self.is_inside_tool_call = True
+                continue
+
+            # -------------------------------------------------------
+            # 2. Function Name: <function=name>
+            # -------------------------------------------------------
+            if current_slice.startswith(self.tool_call_prefix):
+                end_angle = current_slice.find(">")
+                if end_angle != -1:
+                    func_name = current_slice[len(self.tool_call_prefix) : end_angle]
+
+                    self.current_tool_id += 1
+                    self.current_tool_name_sent = True
+                    self.current_tool_param_count = 0
+                    self.json_started = False
+                    self.current_func_name = func_name
+
+                    calls.append(
+                        ToolCallItem(
+                            tool_index=self.current_tool_id,
+                            name=func_name,
+                            parameters="",
+                        )
+                    )
+
+                    self.parsed_pos += end_angle + 1
+                    continue
+                else:
+                    # Incomplete tag
+                    break
+
+            # -------------------------------------------------------
+            # 3. Parameter: <parameter=name>value...
+            # -------------------------------------------------------
+            if current_slice.startswith(self.parameter_prefix):
+                name_end = current_slice.find(">")
+                if name_end != -1:
+                    value_start_idx = name_end + 1
+                    rest_of_slice = current_slice[value_start_idx:]
+
+                    # A parameter can end in multiple ways:
+                    # 1. [Normal] Encounter </parameter>
+                    # 2. [Abnormal] Encounter next <parameter=
+                    # 3. [Abnormal] Encounter </function>
+                    # So we need to find the smallest one as the parameter end position.
+                    cand_end_param = rest_of_slice.find(self.parameter_end_token)
+                    cand_next_param = rest_of_slice.find(self.parameter_prefix)
+                    cand_end_func = rest_of_slice.find(self.function_end_token)
+
+                    candidates = []
+                    if cand_end_param != -1:
+                        candidates.append(
+                            (cand_end_param, len(self.parameter_end_token))
+                        )
+                    if cand_next_param != -1:
+                        candidates.append((cand_next_param, 0))
+                    if cand_end_func != -1:
+                        candidates.append((cand_end_func, 0))
+
+                    if candidates:
+                        best_cand = min(candidates, key=lambda x: x[0])
+                        end_pos = best_cand[0]
+                        end_token_len = best_cand[1]
+
+                        param_name = current_slice[
+                            len(self.parameter_prefix) : name_end
+                        ]
+                        raw_value = rest_of_slice[:end_pos]
+
+                        # Cleanup value
+                        if raw_value.startswith("\n"):
+                            raw_value = raw_value[1:]
+                        if raw_value.endswith("\n"):
+                            raw_value = raw_value[:-1]
+
+                        # JSON Construction
+                        if not self.json_started:
+                            calls.append(
+                                ToolCallItem(
+                                    tool_index=self.current_tool_id, parameters="{"
+                                )
+                            )
+                            self.json_started = True
+
+                        param_config = self._get_arguments_config(
+                            self.current_func_name, tools
+                        )
+                        converted_val = self._convert_param_value(
+                            raw_value, param_name, param_config, self.current_func_name
+                        )
+
+                        # Construct JSON fragment: "key": value
+                        # Note: We must be careful with json.dumps to ensure valid JSON streaming
+                        json_key_val = f"{json.dumps(param_name)}: {json.dumps(converted_val, ensure_ascii=False)}"
+
+                        if self.current_tool_param_count > 0:
+                            fragment = f", {json_key_val}"
+                        else:
+                            fragment = json_key_val
+
+                        calls.append(
+                            ToolCallItem(
+                                tool_index=self.current_tool_id, parameters=fragment
+                            )
+                        )
+                        self.current_tool_param_count += 1
+
+                        # Advance cursor
+                        total_len = (name_end + 1) + end_pos + end_token_len
+                        self.parsed_pos += total_len
+                        continue
+
+                # Incomplete parameter tag or value
+                break
+
+            # -------------------------------------------------------
+            # 4. Function End: </function>
+            # -------------------------------------------------------
+            if current_slice.startswith(self.function_end_token):
+                if not self.json_started:
+                    calls.append(
+                        ToolCallItem(tool_index=self.current_tool_id, parameters="{")
+                    )
+                    self.json_started = True
+
+                calls.append(
+                    ToolCallItem(tool_index=self.current_tool_id, parameters="}")
+                )
+                self.parsed_pos += len(self.function_end_token)
+                self.current_func_name = None
+                continue
+
+            # -------------------------------------------------------
+            # 5. Tool Call End: </tool_call>
+            # -------------------------------------------------------
+            if current_slice.startswith(self.tool_call_end_token):
+                self.parsed_pos += len(self.tool_call_end_token)
+                self.is_inside_tool_call = False  # [FIX] Exit tool call region
+                continue
+
+            # -------------------------------------------------------
+            # 6. Handling content / whitespace / normal text
+            # -------------------------------------------------------
+            # If current position is not the start of a tag (i.e., doesn't start with <), it might be plain text,
+            # or a newline between two tags.
+            # But we need to be careful not to output truncated tags like "<fun" as text.
+
+            next_open_angle = current_slice.find("<")
+
+            if next_open_angle == -1:
+                # This entire segment is plain text
+                if not self.is_inside_tool_call:
+                    normal_text_chunks.append(current_slice)
+                # [FIX] If inside tool call, discard this text (usually \n), don't append
+                self.parsed_pos += len(current_slice)
+                continue
+
+            elif next_open_angle == 0:
+                # Looks like a Tag, but doesn't match any known Tag above
+
+                possible_tags = [
+                    self.tool_call_start_token,
+                    self.tool_call_end_token,
+                    self.tool_call_prefix,
+                    self.function_end_token,
+                    self.parameter_prefix,
+                    self.parameter_end_token,
+                ]
+
+                is_potential_tag = False
+                for tag in possible_tags:
+                    if tag.startswith(current_slice):
+                        is_potential_tag = True
+                        break
+
+                if is_potential_tag:
+                    break  # Wait for more
+                else:
+                    # Just a plain '<' symbol
+                    if not self.is_inside_tool_call:
+                        normal_text_chunks.append("<")
+                    self.parsed_pos += 1
+                    continue
+
+            else:
+                # '<' is in the middle
+                text_segment = current_slice[:next_open_angle]
+                if not self.is_inside_tool_call:
+                    normal_text_chunks.append(text_segment)
+                # [FIX] If inside tool call, discard whitespace/text before Tag
+                self.parsed_pos += next_open_angle
+                continue
+
+        # Memory Cleanup: Slice the buffer
+        # Keep unparsed part, discard parsed part
+        if self.parsed_pos > 0:
+            self._buffer = self._buffer[self.parsed_pos :]
+            self.parsed_pos = 0
+
+        normal_text = "".join(normal_text_chunks) if normal_text_chunks else ""
+        return StreamingParseResult(calls=calls, normal_text=normal_text)
+
+    def supports_structural_tag(self) -> bool:
+        return False
+
+    def structure_info(self) -> _GetInfoFunc:
+        raise NotImplementedError

qwen3coder_tool_parser_vllm.py

@@ -0,0 +1,690 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+import ast
+import json
+import uuid
+from collections.abc import Sequence
+from typing import Any, List, Optional, Union
+
+import regex as re
+
+from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
+                                              ChatCompletionToolsParam,
+                                              DeltaFunctionCall, DeltaMessage,
+                                              DeltaToolCall,
+                                              ExtractedToolCallInformation,
+                                              FunctionCall, ToolCall)
+from vllm.entrypoints.openai.tool_parsers.abstract_tool_parser import (
+    ToolParser, ToolParserManager)
+from vllm.logger import init_logger
+from vllm.transformers_utils.tokenizer import AnyTokenizer
+
+logger = init_logger(__name__)
+
+
+@ToolParserManager.register_module("qwen3_coder")
+class Qwen3CoderToolParser(ToolParser):
+
+    def __init__(self, tokenizer: AnyTokenizer):
+        super().__init__(tokenizer)
+
+        self.current_tool_name_sent: bool = False
+        self.prev_tool_call_arr: list[dict] = []
+        self.current_tool_id: int = -1
+        self.streamed_args_for_tool: list[str] = []
+
+        # Sentinel tokens for streaming mode
+        self.tool_call_start_token: str = "<tool_call>"
+        self.tool_call_end_token: str = "</tool_call>"
+        self.tool_call_prefix: str = "<function="
+        self.function_end_token: str = "</function>"
+        self.parameter_prefix: str = "<parameter="
+        self.parameter_end_token: str = "</parameter>"
+        self.is_tool_call_started: bool = False
+        self.failed_count: int = 0
+
+        # Enhanced streaming state - reset for each new message
+        self._reset_streaming_state()
+
+        # Regex patterns
+        self.tool_call_complete_regex = re.compile(
+            r"<tool_call>(.*?)</tool_call>", re.DOTALL)
+        self.tool_call_regex = re.compile(
+            r"<tool_call>(.*?)</tool_call>|<tool_call>(.*?)$", re.DOTALL)
+        self.tool_call_function_regex = re.compile(
+            r"<function=(.*?)</function>|<function=(.*)$", re.DOTALL)
+        self.tool_call_parameter_regex = re.compile(
+            r"<parameter=(.*?)(?:</parameter>|(?=<parameter=)|(?=</function>)|$)",
+            re.DOTALL)
+
+        if not self.model_tokenizer:
+            raise ValueError(
+                "The model tokenizer must be passed to the ToolParser "
+                "constructor during construction.")
+
+        self.tool_call_start_token_id = self.vocab.get(
+            self.tool_call_start_token)
+        self.tool_call_end_token_id = self.vocab.get(self.tool_call_end_token)
+
+        if self.tool_call_start_token_id is None or self.tool_call_end_token_id is None:
+            raise RuntimeError(
+                "Qwen3 XML Tool parser could not locate tool call start/end "
+                "tokens in the tokenizer!")
+
+        logger.info(
+            f"vLLM Successfully import tool parser {self.__class__.__name__} !"
+        )
+
+    def _generate_tool_call_id(self) -> str:
+        """Generate a unique tool call ID."""
+        return f"call_{uuid.uuid4().hex[:24]}"
+
+    def _reset_streaming_state(self):
+        """Reset all streaming state."""
+        self.current_tool_index = 0
+        self.is_tool_call_started = False
+        self.header_sent = False
+        self.current_tool_id = None
+        self.current_function_name = None
+        self.current_param_name = None
+        self.current_param_value = ""
+        self.param_count = 0
+        self.in_param = False
+        self.in_function = False
+        self.accumulated_text = ""
+        self.json_started = False
+        self.json_closed = False
+        # Store accumulated parameters for type conversion
+        self.accumulated_params = {}
+        self.streaming_request = None
+
+    def _get_arguments_config(
+            self, func_name: str,
+            tools: Optional[list[ChatCompletionToolsParam]]) -> dict:
+        """Extract argument configuration for a function."""
+        if tools is None:
+            return {}
+        for config in tools:
+            if not hasattr(config, "type") or not (hasattr(
+                    config, "function") and hasattr(config.function, "name")):
+                continue
+            if config.type == "function" and config.function.name == func_name:
+                if not hasattr(config.function, "parameters"):
+                    return {}
+                params = config.function.parameters
+                if isinstance(params, dict) and "properties" in params:
+                    return params["properties"]
+                elif isinstance(params, dict):
+                    return params
+                else:
+                    return {}
+        logger.warning(f"Tool '{func_name}' is not defined in the tools list.")
+        return {}
+
+    def _convert_param_value(self, param_value: str, param_name: str,
+                             param_config: dict, func_name: str) -> Any:
+        """Convert parameter value based on its type in the schema."""
+        # Handle null value for any type
+        if param_value.lower() == "null":
+            return None
+
+        if param_name not in param_config:
+            if param_config != {}:
+                logger.warning(
+                    f"Parsed parameter '{param_name}' is not defined in the tool "
+                    f"parameters for tool '{func_name}', directly returning the string value."
+                )
+            return param_value
+
+        if isinstance(param_config[param_name],
+                      dict) and "type" in param_config[param_name]:
+            param_type = str(param_config[param_name]["type"]).strip().lower()
+        else:
+            param_type = "string"
+        if param_type in ["string", "str", "text", "varchar", "char", "enum"]:
+            return param_value
+        elif param_type.startswith("int") or param_type.startswith(
+                "uint") or param_type.startswith(
+                    "long") or param_type.startswith(
+                        "short") or param_type.startswith("unsigned"):
+            try:
+                param_value = int(param_value)
+            except:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' is not an integer in tool "
+                    f"'{func_name}', degenerating to string.")
+            return param_value
+        elif param_type.startswith("num") or param_type.startswith("float"):
+            try:
+                maybe_convert = False if "." in param_value or "e" in param_value.lower() else True
+                param_value: float = float(param_value)
+                if maybe_convert and param_value.is_integer():
+                    param_value = int(param_value)
+            except:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a float in tool "
+                    f"'{func_name}', degenerating to string.")
+            return param_value
+        elif param_type in ["boolean", "bool", "binary"]:
+            param_value = param_value.lower()
+            if param_value not in ["true", "false"]:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a boolean (`true` of `false`) in tool '{func_name}', degenerating to false."
+                )
+            return param_value == "true"
+        else:
+            if param_type in ["object", "array", "arr"
+                              ] or param_type.startswith(
+                                  "dict") or param_type.startswith("list"):
+                try:
+                    param_value = json.loads(param_value)
+                    return param_value
+                except:
+                    logger.warning(
+                        f"Parsed value '{param_value}' of parameter '{param_name}' cannot be parsed with json.loads in tool "
+                        f"'{func_name}', will try other methods to parse it.")
+            try:
+                param_value = ast.literal_eval(param_value)  # safer
+            except:
+                logger.warning(
+                    f"Parsed value '{param_value}' of parameter '{param_name}' cannot be converted via Python `ast.literal_eval()` in tool '{func_name}', degenerating to string."
+                )
+            return param_value
+
+    def _parse_xml_function_call(
+            self, function_call_str: str,
+            tools: Optional[list[ChatCompletionToolsParam]]
+    ) -> Optional[ToolCall]:
+
+        # Extract function name
+        end_index = function_call_str.index(">")
+        function_name = function_call_str[:end_index]
+        param_config = self._get_arguments_config(function_name, tools)
+        parameters = function_call_str[end_index + 1:]
+        param_dict = {}
+        for match_text in self.tool_call_parameter_regex.findall(parameters):
+            idx = match_text.index(">")
+            param_name = match_text[:idx]
+            param_value = str(match_text[idx + 1:])
+            # Remove prefix and trailing \n
+            if param_value.startswith("\n"):
+                param_value = param_value[1:]
+            if param_value.endswith("\n"):
+                param_value = param_value[:-1]
+
+            param_dict[param_name] = self._convert_param_value(
+                param_value, param_name, param_config, function_name)
+        return ToolCall(
+            type="function",
+            function=FunctionCall(name=function_name,
+                                  arguments=json.dumps(param_dict,
+                                                       ensure_ascii=False)),
+        )
+
+    def _get_function_calls(self, model_output: str) -> List[str]:
+        # Find all tool calls
+        matched_ranges = self.tool_call_regex.findall(model_output)
+        raw_tool_calls = [
+            match[0] if match[0] else match[1] for match in matched_ranges
+        ]
+
+        # Back-off strategy if no tool_call tags found
+        if len(raw_tool_calls) == 0:
+            raw_tool_calls = [model_output]
+
+        raw_function_calls = []
+        for tool_call in raw_tool_calls:
+            raw_function_calls.extend(
+                self.tool_call_function_regex.findall(tool_call))
+
+        function_calls = [
+            match[0] if match[0] else match[1] for match in raw_function_calls
+        ]
+        return function_calls
+
+    def extract_tool_calls(
+        self,
+        model_output: str,
+        request: ChatCompletionRequest,
+    ) -> ExtractedToolCallInformation:
+        # Quick check to avoid unnecessary processing
+        if self.tool_call_prefix not in model_output:
+            return ExtractedToolCallInformation(tools_called=False,
+                                                tool_calls=[],
+                                                content=model_output)
+
+        try:
+            function_calls = self._get_function_calls(model_output)
+            if len(function_calls) == 0:
+                return ExtractedToolCallInformation(tools_called=False,
+                                                    tool_calls=[],
+                                                    content=model_output)
+
+            tool_calls = [
+                self._parse_xml_function_call(function_call_str, request.tools)
+                for function_call_str in function_calls
+            ]
+
+            # Populate prev_tool_call_arr for serving layer to set finish_reason
+            self.prev_tool_call_arr.clear()  # Clear previous calls
+            for tool_call in tool_calls:
+                if tool_call:
+                    self.prev_tool_call_arr.append({
+                        "name":
+                        tool_call.function.name,
+                        "arguments":
+                        tool_call.function.arguments,
+                    })
+
+            # Extract content before tool calls
+            content_index = model_output.find(self.tool_call_start_token)
+            content_index = content_index if content_index >= 0 else model_output.find(
+                self.tool_call_prefix)
+            content = model_output[:content_index]  # .rstrip()
+
+            return ExtractedToolCallInformation(
+                tools_called=(len(tool_calls) > 0),
+                tool_calls=tool_calls,
+                content=content if content else None,
+            )
+
+        except Exception:
+            logger.exception("Error in extracting tool call from response.")
+            return ExtractedToolCallInformation(tools_called=False,
+                                                tool_calls=[],
+                                                content=model_output)
+
+    def extract_tool_calls_streaming(
+        self,
+        previous_text: str,
+        current_text: str,
+        delta_text: str,
+        previous_token_ids: Sequence[int],
+        current_token_ids: Sequence[int],
+        delta_token_ids: Sequence[int],
+        request: ChatCompletionRequest,
+    ) -> Union[DeltaMessage, None]:
+        # Store request for type conversion
+        if not previous_text:
+            self._reset_streaming_state()
+            self.streaming_request = request
+
+        # If no delta text, return None unless it's an EOS token after tool calls
+        if not delta_text:
+            # Check if this is an EOS token after all tool calls are complete
+            # We check for tool calls in the text even if is_tool_call_started is False
+            # because it might have been reset after processing all tools
+            if delta_token_ids and self.tool_call_end_token_id not in delta_token_ids:
+                # Count complete tool calls
+                complete_calls = len(
+                    self.tool_call_complete_regex.findall(current_text))
+
+                # If we have completed tool calls and populated prev_tool_call_arr
+                if complete_calls > 0 and len(self.prev_tool_call_arr) > 0:
+                    # Check if all tool calls are closed
+                    open_calls = current_text.count(
+                        self.tool_call_start_token) - current_text.count(
+                            self.tool_call_end_token)
+                    if open_calls == 0:
+                        # Return empty delta message to allow finish_reason processing
+                        return DeltaMessage(content="")
+                elif not self.is_tool_call_started and current_text:
+                    # This is a regular content response that's now complete
+                    return DeltaMessage(content="")
+            return None
+
+        # Update accumulated text
+        self.accumulated_text = current_text
+
+        # Check if we need to advance to next tool
+        if self.json_closed and not self.in_function:
+            # Check if this tool call has ended
+            tool_ends = current_text.count(self.tool_call_end_token)
+            if tool_ends > self.current_tool_index:
+                # This tool has ended, advance to next
+                self.current_tool_index += 1
+                self.header_sent = False
+                self.param_count = 0
+                self.json_started = False
+                self.json_closed = False
+                self.accumulated_params = {}
+
+                # Check if there are more tool calls
+                tool_starts = current_text.count(self.tool_call_start_token)
+                if self.current_tool_index >= tool_starts:
+                    # No more tool calls
+                    self.is_tool_call_started = False
+                # Continue processing next tool
+                return None
+
+        # Handle normal content before tool calls
+        if not self.is_tool_call_started:
+            # Check if tool call is starting
+            if self.tool_call_start_token_id in delta_token_ids or self.tool_call_start_token in delta_text:
+                self.is_tool_call_started = True
+                # Return any content before the tool call
+                if self.tool_call_start_token in delta_text:
+                    content_before = delta_text[:delta_text.index(
+                        self.tool_call_start_token)]
+                    if content_before:
+                        return DeltaMessage(content=content_before)
+                return None
+            else:
+                # Check if we're between tool calls - skip whitespace
+                if current_text.rstrip().endswith(self.tool_call_end_token):
+                    # We just ended a tool call, skip whitespace
+                    if delta_text.strip() == "":
+                        return None
+                # Normal content, no tool call
+                return DeltaMessage(content=delta_text)
+
+        # Check if we're between tool calls (waiting for next one)
+        # Count tool calls we've seen vs processed
+        tool_starts_count = current_text.count(self.tool_call_start_token)
+        if self.current_tool_index >= tool_starts_count:
+            # We're past all tool calls, shouldn't be here
+            return None
+
+        # We're in a tool call, find the current tool call portion
+        # Need to find the correct tool call based on current_tool_index
+        tool_starts = []
+        idx = 0
+        while True:
+            idx = current_text.find(self.tool_call_start_token, idx)
+            if idx == -1:
+                break
+            tool_starts.append(idx)
+            idx += len(self.tool_call_start_token)
+
+        if self.current_tool_index >= len(tool_starts):
+            # No more tool calls to process yet
+            return None
+
+        tool_start_idx = tool_starts[self.current_tool_index]
+        # Find where this tool call ends (or current position if not ended yet)
+        tool_end_idx = current_text.find(self.tool_call_end_token,
+                                         tool_start_idx)
+        if tool_end_idx == -1:
+            tool_text = current_text[tool_start_idx:]
+        else:
+            tool_text = current_text[tool_start_idx:tool_end_idx +
+                                     len(self.tool_call_end_token)]
+
+        # Looking for function header
+        if not self.header_sent:
+            if self.tool_call_prefix in tool_text:
+                func_start = tool_text.find(self.tool_call_prefix) + len(
+                    self.tool_call_prefix)
+                func_end = tool_text.find(">", func_start)
+
+                if func_end != -1:
+                    # Found complete function name
+                    self.current_function_name = tool_text[func_start:func_end]
+                    self.current_tool_id = self._generate_tool_call_id()
+                    self.header_sent = True
+                    self.in_function = True
+
+                    # IMPORTANT: Add to prev_tool_call_arr immediately when we detect a tool call
+                    # This ensures finish_reason="tool_calls" even if parsing isn't complete
+                    already_added = any(
+                        tool.get("name") == self.current_function_name
+                        for tool in self.prev_tool_call_arr)
+                    if not already_added:
+                        self.prev_tool_call_arr.append({
+                            "name": self.current_function_name,
+                            "arguments":
+                            "{}",  # Placeholder, will be updated later
+                        })
+
+                    # Send header with function info
+                    return DeltaMessage(tool_calls=[
+                        DeltaToolCall(
+                            index=self.current_tool_index,
+                            id=self.current_tool_id,
+                            function=DeltaFunctionCall(
+                                name=self.current_function_name, arguments=""),
+                            type="function",
+                        )
+                    ])
+            return None
+
+        # We've sent header, now handle function body
+        if self.in_function:
+            # Send opening brace if not sent yet
+            if not self.json_started and self.parameter_prefix not in delta_text:
+                self.json_started = True
+                return DeltaMessage(tool_calls=[
+                    DeltaToolCall(
+                        index=self.current_tool_index,
+                        function=DeltaFunctionCall(arguments="{"),
+                    )
+                ])
+
+            # Make sure json_started is set if we're processing parameters
+            if not self.json_started:
+                self.json_started = True
+
+            # Check for function end in accumulated text
+            if not self.json_closed and self.function_end_token in tool_text:
+                # Close JSON
+                self.json_closed = True
+
+                # Extract the complete tool call to update prev_tool_call_arr with final arguments
+                # Find the function content
+                func_start = tool_text.find(self.tool_call_prefix) + len(
+                    self.tool_call_prefix)
+                func_content_end = tool_text.find(self.function_end_token,
+                                                  func_start)
+                if func_content_end != -1:
+                    func_content = tool_text[func_start:func_content_end]
+                    # Parse to get the complete arguments
+                    try:
+                        parsed_tool = self._parse_xml_function_call(
+                            func_content, self.streaming_request.tools
+                            if self.streaming_request else None)
+                        if parsed_tool:
+                            # Update existing entry in prev_tool_call_arr with complete arguments
+                            for i, tool in enumerate(self.prev_tool_call_arr):
+                                if tool.get(
+                                        "name") == parsed_tool.function.name:
+                                    self.prev_tool_call_arr[i][
+                                        "arguments"] = parsed_tool.function.arguments
+                                    break
+                    except Exception:
+                        pass  # Ignore parsing errors during streaming
+
+                result = DeltaMessage(tool_calls=[
+                    DeltaToolCall(
+                        index=self.current_tool_index,
+                        function=DeltaFunctionCall(arguments="}"),
+                    )
+                ])
+
+                # Reset state for next tool
+                self.in_function = False
+                self.json_closed = True
+                self.accumulated_params = {}
+
+                return result
+
+            # Look for parameters
+            # Find all parameter starts
+            param_starts = []
+            idx = 0
+            while True:
+                idx = tool_text.find(self.parameter_prefix, idx)
+                if idx == -1:
+                    break
+                param_starts.append(idx)
+                idx += len(self.parameter_prefix)
+
+            # Check if we should start a new parameter
+            if not self.in_param and self.param_count < len(param_starts):
+
+                if len(param_starts) > self.param_count:
+                    # Process the next parameter
+                    param_idx = param_starts[self.param_count]
+                    param_start = param_idx + len(self.parameter_prefix)
+                    remaining = tool_text[param_start:]
+
+                    if ">" in remaining:
+                        # We have the complete parameter name
+                        name_end = remaining.find(">")
+                        self.current_param_name = remaining[:name_end]
+
+                        # Find the parameter value
+                        value_start = param_start + name_end + 1
+                        value_text = tool_text[value_start:]
+                        if value_text.startswith("\n"):
+                            value_text = value_text[1:]
+
+                        # Find where this parameter ends
+                        param_end_idx = value_text.find(
+                            self.parameter_end_token)
+                        if param_end_idx == -1:
+                            # No closing tag, look for next parameter or function end
+                            next_param_idx = value_text.find(
+                                self.parameter_prefix)
+                            func_end_idx = value_text.find(
+                                self.function_end_token)
+
+                            if next_param_idx != -1 and (func_end_idx == -1
+                                                         or next_param_idx
+                                                         < func_end_idx):
+                                param_end_idx = next_param_idx
+                            elif func_end_idx != -1:
+                                param_end_idx = func_end_idx
+                            else:
+                                # Neither found, check if tool call is complete
+                                if self.tool_call_end_token in tool_text:
+                                    # Tool call is complete, so parameter must be complete too
+                                    # Use all remaining text before function end as value
+                                    param_end_idx = len(value_text)
+                                else:
+                                    # Still streaming, wait for more content
+                                    return None
+
+                        if param_end_idx != -1:
+                            # Complete parameter found
+                            param_value = value_text[:param_end_idx]
+                            if param_value.endswith("\n"):
+                                param_value = param_value[:-1]
+
+                            # Store raw value for later processing
+                            self.accumulated_params[
+                                self.current_param_name] = param_value
+
+                            # Get parameter configuration for type conversion
+                            param_config = self._get_arguments_config(
+                                self.current_function_name,
+                                self.streaming_request.tools
+                                if self.streaming_request else None)
+
+                            # Convert the parameter value to the appropriate type
+                            converted_value = self._convert_param_value(
+                                param_value, self.current_param_name,
+                                param_config, self.current_function_name)
+
+                            # Build JSON fragment based on the converted type
+                            # Use json.dumps to properly serialize the value
+                            serialized_value = json.dumps(converted_value,
+                                                          ensure_ascii=False)
+
+                            if self.param_count == 0:
+                                json_fragment = f'"{self.current_param_name}": {serialized_value}'
+                            else:
+                                json_fragment = f', "{self.current_param_name}": {serialized_value}'
+
+                            self.param_count += 1
+
+                            return DeltaMessage(tool_calls=[
+                                DeltaToolCall(
+                                    index=self.current_tool_index,
+                                    function=DeltaFunctionCall(
+                                        arguments=json_fragment),
+                                )
+                            ])
+
+            # Continue parameter value - Not used in the current implementation
+            # since we process complete parameters above
+            if self.in_param:
+                if self.parameter_end_token in delta_text:
+                    # End of parameter
+                    end_idx = delta_text.find(self.parameter_end_token)
+                    value_chunk = delta_text[:end_idx]
+
+                    # Skip past > if at start
+                    if not self.current_param_value and ">" in value_chunk:
+                        gt_idx = value_chunk.find(">")
+                        value_chunk = value_chunk[gt_idx + 1:]
+
+                    if not self.current_param_value and value_chunk.startswith(
+                            "\n"):
+                        value_chunk = value_chunk[1:]
+
+                    # Store complete value
+                    full_value = self.current_param_value + value_chunk
+                    self.accumulated_params[
+                        self.current_param_name] = full_value
+
+                    # Get parameter configuration for type conversion
+                    param_config = self._get_arguments_config(
+                        self.current_function_name,
+                        self.streaming_request.tools
+                        if self.streaming_request else None)
+
+                    # Convert the parameter value to the appropriate type
+                    converted_value = self._convert_param_value(
+                        full_value, self.current_param_name, param_config,
+                        self.current_function_name)
+
+                    # Serialize the converted value
+                    serialized_value = json.dumps(converted_value,
+                                                  ensure_ascii=False)
+
+                    # Since we've been streaming the quoted version, we need to close it properly
+                    # This is complex - for now just complete the value
+                    self.in_param = False
+                    self.current_param_value = ""
+
+                    # Just close the current parameter string
+                    return DeltaMessage(tool_calls=[
+                        DeltaToolCall(
+                            index=self.current_tool_index,
+                            function=DeltaFunctionCall(
+                                arguments='"'),  # Close the string quote
+                        )
+                    ])
+                else:
+                    # Continue accumulating value
+                    value_chunk = delta_text
+
+                    # Handle first chunk after param name
+                    if not self.current_param_value and ">" in value_chunk:
+                        gt_idx = value_chunk.find(">")
+                        value_chunk = value_chunk[gt_idx + 1:]
+
+                    if not self.current_param_value and value_chunk.startswith(
+                            "\n"):
+                        value_chunk = value_chunk[1:]
+
+                    if value_chunk:
+                        # Stream the escaped delta
+                        prev_escaped = json.dumps(
+                            self.current_param_value, ensure_ascii=False
+                        )[1:-1] if self.current_param_value else ""
+                        self.current_param_value += value_chunk
+                        full_escaped = json.dumps(self.current_param_value,
+                                                  ensure_ascii=False)[1:-1]
+                        delta_escaped = full_escaped[len(prev_escaped):]
+
+                        if delta_escaped:
+                            return DeltaMessage(tool_calls=[
+                                DeltaToolCall(
+                                    index=self.current_tool_index,
+                                    function=DeltaFunctionCall(
+                                        arguments=delta_escaped),
+                                )
+                            ])
+
+        return None

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": 1048576,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}