Image-Text-to-Text
Transformers
Safetensors
qwen3_5
autoround
int4
w4g128
w4a16
quantization
vllm
multimodal
mtp
speculative-decoding
code
coding
conversational
4-bit precision
auto-round
Instructions to use webhie/Qwen3.6-27B-int4-AutoRound-Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="webhie/Qwen3.6-27B-int4-AutoRound-Code") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("webhie/Qwen3.6-27B-int4-AutoRound-Code") model = AutoModelForMultimodalLM.from_pretrained("webhie/Qwen3.6-27B-int4-AutoRound-Code", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "webhie/Qwen3.6-27B-int4-AutoRound-Code" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webhie/Qwen3.6-27B-int4-AutoRound-Code", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/webhie/Qwen3.6-27B-int4-AutoRound-Code
- SGLang
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "webhie/Qwen3.6-27B-int4-AutoRound-Code" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webhie/Qwen3.6-27B-int4-AutoRound-Code", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "webhie/Qwen3.6-27B-int4-AutoRound-Code" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webhie/Qwen3.6-27B-int4-AutoRound-Code", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use webhie/Qwen3.6-27B-int4-AutoRound-Code with Docker Model Runner:
docker model run hf.co/webhie/Qwen3.6-27B-int4-AutoRound-Code
| {%- set image_count = namespace(value=0) %} | |
| {%- set video_count = namespace(value=0) %} | |
| {%- macro render_content(content, do_vision_count, is_system_content=false) %} | |
| {%- if content is string %} | |
| {{- content }} | |
| {%- elif content is iterable and content is not mapping %} | |
| {%- for item in content %} | |
| {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} | |
| {%- if is_system_content %} | |
| {{- raise_exception('System message cannot contain images.') }} | |
| {%- endif %} | |
| {%- if do_vision_count %} | |
| {%- set image_count.value = image_count.value + 1 %} | |
| {%- endif %} | |
| {%- if add_vision_id is defined and add_vision_id %} | |
| {{- 'Picture ' ~ image_count.value ~ ': ' }} | |
| {%- endif %} | |
| {{- '<|vision_start|><|image_pad|><|vision_end|>' }} | |
| {%- elif 'video' in item or item.type == 'video' %} | |
| {%- if is_system_content %} | |
| {{- raise_exception('System message cannot contain videos.') }} | |
| {%- endif %} | |
| {%- if do_vision_count %} | |
| {%- set video_count.value = video_count.value + 1 %} | |
| {%- endif %} | |
| {%- if add_vision_id is defined and add_vision_id %} | |
| {{- 'Video ' ~ video_count.value ~ ': ' }} | |
| {%- endif %} | |
| {{- '<|vision_start|><|video_pad|><|vision_end|>' }} | |
| {%- elif 'text' in item %} | |
| {{- item.text }} | |
| {%- else %} | |
| {{- raise_exception('Unexpected item type in content.') }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- elif content is none or content is undefined %} | |
| {{- '' }} | |
| {%- else %} | |
| {{- raise_exception('Unexpected content type.') }} | |
| {%- endif %} | |
| {%- endmacro %} | |
| {%- set ns_flags = namespace(enable_thinking=true, has_tools=false) %} | |
| {%- if enable_thinking is defined %} | |
| {%- set ns_flags.enable_thinking = enable_thinking %} | |
| {%- endif %} | |
| {%- if not messages %} | |
| {{- raise_exception('No messages provided.') }} | |
| {%- endif %} | |
| {%- set system_content = '' %} | |
| {%- set has_system = false %} | |
| {%- if messages[0].role == 'system' or messages[0].role == 'developer' %} | |
| {%- set has_system = true %} | |
| {%- set system_content = render_content(messages[0].content, false, true)|trim %} | |
| {%- if '<|think_off|>' in system_content %} | |
| {%- set ns_flags.enable_thinking = false %} | |
| {%- set system_content = system_content | replace('<|think_off|>', '') %} | |
| {%- endif %} | |
| {%- if '<|think_on|>' in system_content %} | |
| {%- set ns_flags.enable_thinking = true %} | |
| {%- set system_content = system_content | replace('<|think_on|>', '') %} | |
| {%- endif %} | |
| {%- set system_content = system_content | trim %} | |
| {%- endif %} | |
| {%- if tools and tools is iterable and tools is not mapping %} | |
| {%- set ns_flags.has_tools = true %} | |
| {{- '<|im_start|>system\n' }} | |
| {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }} | |
| {%- for tool in tools %} | |
| {%- set fn = tool.function if tool.function is defined else tool %} | |
| {%- set props = {} %} | |
| {%- set req = [] %} | |
| {%- if fn.parameters is defined and fn.parameters is mapping %} | |
| {%- if fn.parameters.properties is defined %} | |
| {%- set props = fn.parameters.properties %} | |
| {%- endif %} | |
| {%- if fn.parameters.required is defined %} | |
| {%- set req = fn.parameters.required %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set ns_p = namespace(sig='') %} | |
| {%- for pname in props %} | |
| {%- set pdef = props[pname] %} | |
| {%- set ptype = 'any' %} | |
| {%- if pdef.type is defined %} | |
| {%- if pdef.type == 'array' or pdef.type == 'object' %} | |
| {%- set ptype = 'array|object' %} | |
| {%- elif pdef.enum is defined and pdef.enum is iterable and pdef.enum is not string and pdef.enum is not mapping %} | |
| {%- set ptype = pdef.enum | join('|') %} | |
| {%- else %} | |
| {%- set ptype = pdef.type %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set part = pname ~ ('' if pname in req else '?') ~ ': ' ~ ptype %} | |
| {%- set ns_p.sig = ns_p.sig ~ ', ' ~ part if ns_p.sig else part %} | |
| {%- endfor %} | |
| {{- '\n- ' ~ fn.name ~ '(' ~ ns_p.sig ~ ')' }} | |
| {%- if fn.description is defined %} | |
| {{- ' — ' ~ fn.description }} | |
| {%- endif %} | |
| {%- if fn.parameters is defined and fn.parameters is mapping %} | |
| {%- for pname in props %} | |
| {%- set pdef = props[pname] %} | |
| {%- if pdef.type is defined and (pdef.type == 'array' or pdef.type == 'object') %} | |
| {{- '\n - ' ~ pname ~ ' schema: ' ~ pdef | tojson }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- endif %} | |
| {%- 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>' }} | |
| {%- if has_system and system_content %} | |
| {{- '\n\n' + system_content }} | |
| {%- endif %} | |
| {{- '<|im_end|>\n' }} | |
| {%- elif has_system and system_content %} | |
| {{- '<|im_start|>system\n' + system_content + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- for message in messages %} | |
| {%- set is_system = (message.role == "system" or message.role == "developer") %} | |
| {%- set content = render_content(message.content, true, is_system)|trim %} | |
| {%- if '<|think_off|>' in content %} | |
| {%- set ns_flags.enable_thinking = false %} | |
| {%- set content = content | replace('<|think_off|>', '') | trim %} | |
| {%- elif '<|think_on|>' in content %} | |
| {%- set ns_flags.enable_thinking = true %} | |
| {%- set content = content | replace('<|think_on|>', '') | trim %} | |
| {%- endif %} | |
| {%- if is_system %} | |
| {%- if not loop.first and content %} | |
| {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- elif message.role == "user" %} | |
| {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' }} | |
| {%- elif message.role == "assistant" %} | |
| {%- set reasoning_content = '' %} | |
| {%- if message.reasoning_content is string %} | |
| {%- set reasoning_content = message.reasoning_content %} | |
| {%- else %} | |
| {%- if '</think>' in content or '</thinking>' in content %} | |
| {%- set think_end_token = '</think>' if '</think>' in content else '</thinking>' %} | |
| {%- set reasoning_parts = content.split(think_end_token) %} | |
| {%- set reasoning_content = reasoning_parts[0] %} | |
| {%- set content = reasoning_parts[1] %} | |
| {%- if '<think>' in reasoning_content %} | |
| {%- set reasoning_content = reasoning_content.split('<think>')[1] %} | |
| {%- endif %} | |
| {%- elif '<think>' in content %} | |
| {%- if '<tool_call>' in content %} | |
| {%- set content = content | replace('<tool_call>', '</think>\n<tool_call>', 1) %} | |
| {%- set reasoning_parts = content.split('</think>') %} | |
| {%- set reasoning_content = reasoning_parts[0] %} | |
| {%- set content = reasoning_parts[1] %} | |
| {%- if '<think>' in reasoning_content %} | |
| {%- set reasoning_content = reasoning_content.split('<think>')[1] %} | |
| {%- endif %} | |
| {%- else %} | |
| {%- set reasoning_content = content.split('<think>')[1] %} | |
| {%- set content = '' %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set reasoning_content = reasoning_content | trim %} | |
| {%- set content = content | trim %} | |
| {%- set show_think = false %} | |
| {%- if reasoning_content %} | |
| {%- if preserve_thinking is defined and preserve_thinking %} | |
| {%- set show_think = true %} | |
| {%- elif loop.last %} | |
| {%- set show_think = true %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if show_think %} | |
| {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }} | |
| {%- else %} | |
| {{- '<|im_start|>' + message.role + '\n' + content }} | |
| {%- endif %} | |
| {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} | |
| {%- for tool_call in message.tool_calls %} | |
| {%- if tool_call.function is defined %} | |
| {%- set tool_call = tool_call.function %} | |
| {%- endif %} | |
| {%- if loop.first and content %} | |
| {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }} | |
| {%- else %} | |
| {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }} | |
| {%- endif %} | |
| {%- if tool_call.arguments is defined and tool_call.arguments is mapping %} | |
| {%- if tool_call.arguments|length > 0 %} | |
| {%- for args_name in tool_call.arguments %} | |
| {%- set args_value = tool_call.arguments[args_name] %} | |
| {{- '<parameter=' + args_name + '>\n' }} | |
| {%- set args_value = args_value | tojson if args_value is mapping or (args_value is iterable and args_value is not string) else args_value | string %} | |
| {{- args_value }} | |
| {{- '\n</parameter>\n' }} | |
| {%- endfor %} | |
| {%- endif %} | |
| {%- elif tool_call.arguments is defined and tool_call.arguments is string %} | |
| {%- if tool_call.arguments|trim|length > 0 %} | |
| {{- tool_call.arguments }} | |
| {{- '\n' }} | |
| {%- endif %} | |
| {%- 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 ns_flags.enable_thinking is false %} | |
| {{- '<think>\n\n</think>\n\n' }} | |
| {%- else %} | |
| {{- '<think>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |