Upload folder using huggingface_hub

.md5sum_check.txt

@@ -0,0 +1,23 @@
+8201bac8e860371f21828edb916d1ea4  config.json
+9c968e401c7939ca4692bc44d5c74fc4  generation_config.json
+e78882c2e224a75fa8180ec610bae243  merges.txt
+5389e393fdb43e2584f96cfd91314211  model-00001-of-00016.safetensors
+85e3ac5139eca812d8afc052a0e2c3ea  model-00002-of-00016.safetensors
+5f74e4d0e1e24e727be1b1140cabded8  model-00003-of-00016.safetensors
+1c9dacece675762d7cdde9e29bdffa15  model-00004-of-00016.safetensors
+9a2c57b55efc2c93a92ce158e629a86f  model-00005-of-00016.safetensors
+7edf60f79dacb69d6d77c2f066f81a66  model-00006-of-00016.safetensors
+69492bad402a57e39f4f077a4fc6ec3b  model-00007-of-00016.safetensors
+62b14f82a811e22cb58b09991c2f8472  model-00008-of-00016.safetensors
+6b8f9d0d35393c84265dfb0dbfd50ecd  model-00009-of-00016.safetensors
+a7a695a30042b463e2f678b3f85a681d  model-00010-of-00016.safetensors
+afc6388bdde260234590360c0dae4cc0  model-00011-of-00016.safetensors
+f1744a631b88edfa91e26ac42ecf2d39  model-00012-of-00016.safetensors
+aa1c3243355a32fb0698729f10251480  model-00013-of-00016.safetensors
+8f9d5601a39e9d6b9f48e54c397b5e4b  model-00014-of-00016.safetensors
+1143f7425b586f1bfc2849bf581f0713  model-00015-of-00016.safetensors
+53afc3d0f64107cc311bc504eb2264e7  model-00016-of-00016.safetensors
+7b4abccdab64e25378857f99d8865427  model.safetensors.index.json
+bb56be867dd18d6d8a09109fc32f14a3  tokenizer.json
+21e83e6a6f3551952ead285d989ba204  tokenizer_config.json
+613b8e4a622c4a2c90e9e1245fc540d6  vocab.json

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5472,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "qkv_bias": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.0,
+  "shared_expert_intermediate_size": 0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f4ee157c2bdb00521d0f422c08ef16f0f3f5f7e234786d829401d627d2e167
+size 3998893112

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf85f0e5a0ea8d8cd3fd1f411175d811ca735571210873fd42bb5eec0b35406
+size 3999974192

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa5cc233e965c8671d32a335045697fc4317c8d2939d8ca5fb9ef62d0233207
+size 3997360832

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10ff15f08abea0ff60b2fc345dcc34191bc8049d05d3bece6b081a99cbfc4c8
+size 3999975056

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d3701e2354a8cf6e5afa3f84520bf81effcdc29b0c481dbbeb089f80349100
+size 3999975400

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c832bf9e527b7b6f3184b561de05f30981bdcfdffe9c69e69064cdaa97071b5
+size 3999975400

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a710c3ff52e85d22ae3f5b10b9a4dd49821c9533460fb1d4bb21593f71b585
+size 3999975472

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2861625e1bd8a212151445072b9d826c9754fd4618f8b83c2857fc0854b778
+size 3997362064

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8335225fd61c0fe283a83463a8d9c5c19e211ea8048925b031a088f274eb9c4e
+size 3999975408

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421481c42e8d85891c9d88492d7530d6b6d8b15c23a6db6a9b7438e0b6161330
+size 3999975400

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7dd447928ddec67a3ec06d5bc4fd99dde9ac5bdf0b6ab500faca5dfdfb963b4
+size 3999975408

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349a0b0247d244ffef34bc23b403ce756f515242323f024a5f8028c109a798af
+size 3987924896

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e7f570649b27bc35b8cd27ac643d2158c02a5c76078c80a8afc449377b508e
+size 3999975088

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b30aed1b55b3f25fbf2c5e81784438d0a08461c9518e26e11987eb10d80ebd7
+size 3999975400

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8b3b13c0519874ed0cbe6832ab57e51476e3821c83f0ffe4ec83a8d23fc5f4
+size 3999975400

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778479fa2b8b766ba1c7bfc56a71ed9b060081e0fbc5eb4edafd19a1d6b4c116
+size 1085307128

qwen3coder_tool_parser.py

@@ -0,0 +1,675 @@
+# SPDX-License-Identifier: Apache-2.0
+
+import json
+import re
+import uuid
+from collections.abc import Sequence
+from typing import Union, Optional, Any, List, Dict
+from enum import Enum
+
+from vllm.entrypoints.openai.protocol import (
+    ChatCompletionRequest,
+    ChatCompletionToolsParam,
+    DeltaMessage,
+    DeltaToolCall,
+    DeltaFunctionCall,
+    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_xml")
+class Qwen3XMLToolParser(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=(.*?)$", 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
+
+    def _parse_xml_function_call(
+        self, function_call_str: str, tools: Optional[list[ChatCompletionToolsParam]]
+    ) -> Optional[ToolCall]:
+        def get_arguments_config(func_name: str) -> dict:
+            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(
+            param_value: str, param_name: str, param_config: dict, func_name: str
+        ) -> Any:
+            # 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:
+                    float_param_value = float(param_value)
+                    param_value = float_param_value if float_param_value - int(float_param_value) != 0 else int(float_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 == "object" or param_type.startswith("dict"):
+                    try:
+                        param_value = json.loads(param_value)
+                        return param_value
+                    except:
+                        logger.warning(
+                            f"Parsed value '{param_value}' of parameter '{param_name}' is not a valid JSON object in tool "
+                            f"'{func_name}', will try other methods to parse it."
+                        )
+                try:
+                    param_value = eval(param_value)
+                except:
+                    logger.warning(
+                        f"Parsed value '{param_value}' of parameter '{param_name}' cannot be converted via Python `eval()` in tool '{func_name}', degenerating to string."
+                    )
+                return param_value
+
+        # Extract function name
+        end_index = function_call_str.index(">")
+        function_name = function_call_str[:end_index]
+        param_config = get_arguments_config(function_name)
+        parameters = function_call_str[end_index + 1 :]
+        param_dict = {}
+        for match in self.tool_call_parameter_regex.findall(parameters):
+            match_text = match[0] if match[0] else match[1]
+            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] = 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]:
+        # 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
+
+        # Check if this is the first call (reset state if needed)
+        if not previous_text:
+            self._reset_streaming_state()
+
+        # 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
+
+                # 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 not self.parameter_prefix 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, request.tools if 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
+
+                return result
+
+            # Look for parameters
+            # Count how many complete parameters we have processed
+            complete_params = tool_text.count(self.parameter_end_token)
+
+            # Check if we should start a new parameter
+            if not self.in_param and self.param_count < complete_params:
+                # Find the unprocessed parameter
+                # Count 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)
+
+                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:
+                            # Complete parameter found
+                            param_value = value_text[:param_end_idx]
+                            if param_value.endswith("\n"):
+                                param_value = param_value[:-1]
+
+                            # Build complete JSON fragment for this parameter
+                            if self.param_count == 0:
+                                json_fragment = (
+                                    '"'
+                                    + self.current_param_name
+                                    + '": "'
+                                    + json.dumps(param_value)[1:-1]
+                                    + '"'
+                                )
+                            else:
+                                json_fragment = (
+                                    ', "'
+                                    + self.current_param_name
+                                    + '": "'
+                                    + json.dumps(param_value)[1:-1]
+                                    + '"'
+                                )
+
+                            self.param_count += 1
+
+                            return DeltaMessage(
+                                tool_calls=[
+                                    DeltaToolCall(
+                                        index=self.current_tool_index,
+                                        function=DeltaFunctionCall(
+                                            arguments=json_fragment
+                                        ),
+                                    )
+                                ]
+                            )
+
+            # Continue parameter value
+            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:]
+
+                    # Calculate incremental JSON
+                    full_value = self.current_param_value + value_chunk
+                    prev_escaped = (
+                        json.dumps(self.current_param_value)[1:-1]
+                        if self.current_param_value
+                        else ""
+                    )
+                    full_escaped = json.dumps(full_value)[1:-1]
+                    delta_escaped = full_escaped[len(prev_escaped) :]
+
+                    self.in_param = False
+                    self.current_param_value = ""
+
+                    return DeltaMessage(
+                        tool_calls=[
+                            DeltaToolCall(
+                                index=self.current_tool_index,
+                                function=DeltaFunctionCall(
+                                    arguments=delta_escaped + '"'
+                                ),
+                            )
+                        ]
+                    )
+                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)[1:-1]
+                            if self.current_param_value
+                            else ""
+                        )
+                        self.current_param_value += value_chunk
+                        full_escaped = json.dumps(self.current_param_value)[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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+    "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,
+    "chat_template": "{% macro render_item_list(item_list, tag_name='required') %}\n    {%- if item_list is defined and item_list is iterable and item_list | length > 0 %}\n        {%- if tag_name %}{{- '\\n<' ~ tag_name ~ '>' -}}{% endif %}\n            {{- '[' }}\n                {%- for item in item_list -%}\n                    {%- if loop.index > 1 %}{{- \", \"}}{% endif -%}\n                    {%- if item is string -%}\n                        {{ \"`\" ~ item ~ \"`\" }}\n                    {%- else -%}\n                        {{ item }}\n                    {%- endif -%}\n                {%- endfor -%}\n            {{- ']' }}\n        {%- if tag_name %}{{- '</' ~ tag_name ~ '>' -}}{% endif %}\n    {%- endif %}\n{% endmacro %}\n\n{%- if messages[0][\"role\"] == \"system\" %}\n    {%- set system_message = messages[0][\"content\"] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{%- if not tools is defined %}\n    {%- set tools = [] %}\n{%- endif %}\n\n{%- if system_message is defined %}\n    {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n    {%- if tools is iterable and tools | length > 0 %}\n        {{- \"<|im_start|>system\\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks.\" }}\n    {%- endif %}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n    {{- \"\\n\\nYou have access to the following functions:\\n\\n\" }}\n    {{- \"<tools>\" }}\n    {%- for tool in tools %}\n        {%- if tool.function is defined %}\n            {%- set tool = tool.function %}\n        {%- endif %}\n        {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n        {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n        {{- '\\n<parameters>' }}\n        {%- for param_name, param_fields in tool.parameters.properties|items %}\n            {{- '\\n<parameter>' }}\n            {{- '\\n<name>' ~ param_name ~ '</name>' }}\n            {%- if param_fields.type is defined %}\n                {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n            {%- endif %}\n            {%- if param_fields.description is defined %}\n                {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n            {%- endif %}\n            {{- render_item_list(param_fields.enum, 'enum') }}\n            {%- set handled_keys = ['type', 'description', 'enum', 'required'] %}\n            {%- for json_key in param_fields.keys() | reject(\"in\", handled_keys) %}\n                {%- set normed_json_key = json_key | replace(\"-\", \"_\") | replace(\" \", \"_\") | replace(\"$\", \"\") %}\n                {%- if param_fields[json_key] is mapping %}\n                    {{- '\\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | tojson | safe) ~ '</' ~ normed_json_key ~ '>' }}\n                {%- else %}\n                    {{-'\\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | string) ~ '</' ~ normed_json_key ~ '>' }}\n                {%- endif %}\n            {%- endfor %}\n            {{- render_item_list(param_fields.required, 'required') }}\n            {{- '\\n</parameter>' }}\n        {%- endfor %}\n        {{- render_item_list(tool.parameters.required, 'required') }}\n        {{- '\\n</parameters>' }}\n        {%- if tool.return is defined %}\n            {%- if tool.return is mapping %}\n                {{- '\\n<return>' ~ (tool.return | tojson | safe) ~ '</return>' }}\n            {%- else %}\n                {{- '\\n<return>' ~ (tool.return | string) ~ '</return>' }}\n            {%- endif %}\n        {%- endif %}\n        {{- '\\n</function>' }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n{%- endif %}\n{%- if system_message is defined %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if tools is iterable and tools | length > 0 %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in loop_messages %}\n    {%- if message.role == \"assistant\" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}\n            {{- '\\n' + message.content | trim + '\\n' }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n            {%- if tool_call.arguments is defined %}\n                {%- for args_name, args_value in tool_call.arguments|items %}\n                    {{- '<parameter=' + args_name + '>\\n' }}\n                    {%- set args_value = args_value if args_value is string else args_value | string %}\n                    {{- args_value }}\n                    {{- '\\n</parameter>\\n' }}\n                {%- endfor %}\n            {%- endif %}\n            {{- '</function>\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"user\" or message.role == \"system\" or message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user\\n' }}\n        {%- endif %}\n        {{- '<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>\\n' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 1048576,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false
+}