Skip to content

Implemented Qwen35ChatHandler for Qwen3.5 #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JamePeng merged 8 commits into from
Mar 1, 2026
+199 −11
Merged

Implemented Qwen35ChatHandler for Qwen3.5 #61

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
af3d8bd
updated template
alcoftTAO Feb 26, 2026
8a2395a
Merge branch 'JamePeng:main' into main
alcoftTAO Feb 27, 2026
60e1015
tested chat template, changed some parameters
alcoftTAO Feb 27, 2026
e5dbfad
Merge branch 'JamePeng:main' into main
alcoftTAO Feb 27, 2026
6286f7b
updated chat template.
alcoftTAO Feb 28, 2026
3698316
Merge branch 'JamePeng:main' into main
alcoftTAO Feb 28, 2026
db6ee16
Merge branch 'JamePeng:main' into main
alcoftTAO Mar 1, 2026
2258973
update chat handler
alcoftTAO Mar 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
210 changes: 199 additions & 11 deletions llama_cpp/llama_chat_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4669,7 +4669,6 @@ def __init__(
self,
force_reasoning: bool = False,
add_vision_id: bool = True,
image_min_tokens: int = -1,
**kwargs,
):
"""
Expand All @@ -4680,20 +4679,13 @@ def __init__(
- add_vision_id (bool):
- True (default): Count all the images. Recommended for multi-image.
- False: Doesn't count the images. Can save tokens with single-image.
- image_min_tokens (int):
It only takes effect when the value is greater than zero. the default value is -1 (i.e., using the default parameters in the model's preprocessor_config.json).
Note: Qwen-VL models require at minimum 1024 image tokens to function correctly on bbox grounding tasks
"""
super().__init__(**kwargs)
self.force_reasoning = force_reasoning
self.add_vision_id = add_vision_id
self.image_min_tokens = image_min_tokens

super().__init__(image_min_tokens=self.image_min_tokens, **kwargs)
self.extra_template_arguments["force_reasoning"] = force_reasoning
self.extra_template_arguments["add_vision_id"] = add_vision_id

def __call__(self, **kwargs):
self.extra_template_arguments["force_reasoning"] = self.force_reasoning
self.extra_template_arguments["add_vision_id"] = self.add_vision_id

llama = kwargs['llama']

if hasattr(llama, 'input_ids'):
Expand All @@ -4705,6 +4697,202 @@ def __call__(self, **kwargs):
# Use parent implementation
return super().__call__(**kwargs)

class Qwen35ChatHandler(MTMDChatHandler):
CHAT_FORMAT = (
"{%- set image_count = namespace(value=0) -%}"
"{%- set video_count = namespace(value=0) -%}"
"{%- macro render_content(content, do_vision_count, is_system_content=false) -%}"
" {%- if content is string -%}"
" {{- content -}}"
" {%- elif content is iterable and content is not mapping -%}"
" {%- for item in content -%}"
" {%- if 'image_url' in item or item.type == 'image_url' -%}"
" {%- if is_system_content -%}"
" {{- raise_exception('System message cannot contain images.') -}}"
" {%- endif -%}"
" {%- if do_vision_count -%}"
" {%- set image_count.value = image_count.value + 1 -%}"
" {%- endif -%}"
" {%- if add_vision_id -%}"
" {{- 'Picture ' -}}"
" {{- image_count.value | string -}}"
" {{- ': ' -}}"
" {%- endif -%}"
" {{- '<|vision_start|>' -}}"
" {%- if item.image_url is string -%}"
" {{- item.image_url -}}"
" {%- else -%}"
" {{- item.image_url.url -}}"
" {%- endif -%}"
" {{- '<|vision_end|>' -}}"
" {%- elif 'video' in item -%}"
" {{- raise_exception('llama.cpp does not currently support video.') -}}" # Video not supported, raise exception
" {%- if is_system_content -%}"
" {{- raise_exception('System message cannot contain videos.') -}}"
" {%- endif -%}"
" {%- if do_vision_count -%}"
" {%- set video_count.value = video_count.value + 1 -%}"
" {%- endif -%}"
" {%- if add_vision_id -%}"
" {{- 'Video ' ~ video_count.value ~ ': ' -}}"
" {%- endif -%}"
" {{- '<|vision_start|>' -}}"
" {{- item.video -}}"
" {{- '<|vision_end|>' -}}"
" {%- elif 'text' in item -%}"
" {{- item.text -}}"
" {%- else -%}"
" {{- raise_exception('Unexpected item type in content.') -}}"
" {%- endif -%}"
" {%- endfor -%}"
" {%- elif content is none or content is undefined -%}"
" {{- '' -}}"
" {%- else -%}"
" {{- raise_exception('Unexpected content type.') -}}"
" {%- endif -%}"
"{%- endmacro -%}"
"{%- if not messages -%}"
" {{- raise_exception('No messages provided.') -}}"
"{%- endif -%}"
"{%- if tools and tools is iterable and tools is not mapping -%}"
" {{- '<|im_start|>system\n' -}}"
" {{- '# Tools\n\nYou have access to the following functions:\n\n<tools>' -}}"
" {%- for tool in tools -%}"
" {{- '\n' -}}"
" {{- tool | tojson -}}"
" {%- endfor -%}"
" {{- '\n</tools>' -}}"
" {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' -}}"
" {%- if messages[0].role == 'system' -%}"
" {%- set content = render_content(messages[0].content, false, true) | trim -%}"
" {%- if content -%}"
" {{- '\n\n' + content -}}"
" {%- endif -%}"
" {%- endif -%}"
" {{- '<|im_end|>\n' -}}"
"{%- elif messages[0].role == 'system' -%}"
" {%- set content = render_content(messages[0].content, false, true) -%}"
" {{- '<|im_start|>system\n' + content + '<|im_end|>\n' -}}"
"{%- endif -%}"
"{%- set ns = namespace(multi_step_tool=true, last_query_index=messages | length - 1) -%}"
"{%- for message in messages[::-1] -%}"
" {%- set index = messages | length - 1 - loop.index0 -%}"
" {%- if ns.multi_step_tool and message.role == 'user' -%}"
" {%- set content = render_content(message.content, false) | trim -%}"
" {%- if not (content.startswith('<tool_response>') and content.endswith('</tool_response>')) -%}"
" {%- set ns.multi_step_tool = false -%}"
" {%- set ns.last_query_index = index -%}"
" {%- endif -%}"
" {%- endif -%}"
"{%- endfor -%}"
"{%- if ns.multi_step_tool -%}"
" {{- raise_exception('No user query found in messages.') -}}"
"{%- endif -%}"
"{%- for message in messages -%}"
" {%- set content = render_content(message.content, true) | trim -%}"
" {%- if message.role == 'system' -%}"
" {%- if not loop.first -%}"
" {{- raise_exception('System message must be at the beginning.') -}}"
" {%- endif -%}"
" {%- elif message.role == 'user' -%}"
" {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' -}}"
" {%- elif message.role == 'assistant' -%}"
" {%- set reasoning_content = '' -%}"
" {%- if message.reasoning_content is string -%}"
" {%- set reasoning_content = message.reasoning_content -%}"
" {%- elif '</think>' in content -%}"
" {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') -%}"
" {%- set content = content.split('</think>')[-1].lstrip('\n') -%}"
" {%- endif -%}"
" {%- set reasoning_content = reasoning_content | trim -%}"
" {%- if loop.index0 > ns.last_query_index -%}"
" {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content -}}"
" {%- else -%}"
" {{- '<|im_start|>' + message.role + '\n' + content -}}"
" {%- endif -%}"
" {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping -%}"
" {%- for tool_call in message.tool_call -%}"
" {%- if tool_call.function is defined -%}"
" {%- set tool_call = tool_call.function -%}"
" {%- endif -%}"
" {%- if loop.first -%}"
" {%- if content | trim -%}"
" {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' -}}"
" {%- else -%}"
" {{- '<tool_call>\n<function=' + tool_call.name + '>\n' -}}"
" {%- endif -%}"
" {%- else -%}"
" {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' -}}"
" {%- endif -%}"
" {%- if tool_call.arguments is defined -%}"
" {%- for (args_name, args_value) in tool_calls.arguments | items -%}"
" {{- '<parameter=' + args.name + '>\n' -}}"
" {%- set args_value = args_value | tojson | safe if args_value is mapping or args_value is sequence and args_value is not string else args_value | string -%}"
" {{- args_value -}}"
" {{- '\n</parameter>' -}}"
" {%- endfor -%}"
" {%- endif -%}"
" {{- '</function>\n</tool_call>' -}}"
" {%- endfor -%}"
" {%- endif -%}"
" {{- '<|im_end|>\n' -}}"
" {%- elif message.role == 'tool' -%}"
" {%- if loop.previtem and loop.previtem.role != 'tool' -%}"
" {{- '<|im_start|>user' -}}"
" {%- endif -%}"
" {{- '\n<tool_response>\n' -}}"
" {{- content -}}"
" {{- '\n</tool_response>' -}}"
" {%- if not loop.last and loop.nextitem.role != 'tool' -%}"
" {{- '<|im_end|>\n' -}}"
" {%- elif loop.last -%}"
" {{- '<|im_end|>\n' -}}"
" {%- endif -%}"
" {%- else -%}"
" {{- raise_exception('Unexpected message role.') -}}"
" {%- endif -%}"
"{%- endfor -%}"
"{%- if add_generation_prompt -%}"
" {{- '<|im_start|>assistant\n' -}}"
" {%- if enable_thinking is false -%}"
" {{- '<think>\n\n</think>\n\n' -}}"
" {%- else -%}"
" {{- '<think>\n' -}}"
" {%- endif -%}"
"{%- endif -%}"
)

def __init__(
self,
enable_thinking: bool = True,
add_vision_id: bool = True,
**kwargs,
):
"""
Parameters:
- enable_thinking (bool):
- True (default): Enables reasoning for better results.
- False: Disables reasoning for faster results.
- add_vision_id (bool):
- True (default): Count all the images. Recommended for multi-image.
- False: Doesn't count the images. Can save tokens with single-image.
"""
super().__init__(**kwargs)
self.enable_thinking = enable_thinking
self.extra_template_arguments["enable_thinking"] = enable_thinking
self.extra_template_arguments["add_vision_id"] = add_vision_id

def __call__(self, **kwargs):
llama = kwargs['llama']

if hasattr(llama, 'input_ids'):
llama.input_ids.fill(0)

if self.verbose:
print(f"{self.log_prefix}(enable_thinking={self.enable_thinking}) - Start processing")

# Use parent implementation
return super().__call__(**kwargs)

@register_chat_completion_handler("chatml-function-calling")
def chatml_function_calling(
Expand Down