Instructions to use Qwen/Qwen3.8-Flash-Next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3.8-Flash-Next with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.8-Flash-Next") 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3.8-Flash-Next") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.8-Flash-Next", 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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Qwen/Qwen3.8-Flash-Next with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen3.8-Flash-Next" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen3.8-Flash-Next", "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/Qwen/Qwen3.8-Flash-Next
- SGLang
How to use Qwen/Qwen3.8-Flash-Next 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 "Qwen/Qwen3.8-Flash-Next" \ --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": "Qwen/Qwen3.8-Flash-Next", "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 "Qwen/Qwen3.8-Flash-Next" \ --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": "Qwen/Qwen3.8-Flash-Next", "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 Qwen/Qwen3.8-Flash-Next with Docker Model Runner:
docker model run hf.co/Qwen/Qwen3.8-Flash-Next
Commit ·
812d96e
1
Parent(s): 7ecef55
Add a response template and generation tags (#81)
Browse files- Add a response template (df589464e5c3b8f11e703094e32a81ff82f33406)
- Update chat_template.jinja (eb0e3d3b66359c894a52ce23336b904f68f7142a)
Co-authored-by: Matthew Carrigan <Rocketknight1@users.noreply.huggingface.co>
- chat_template.jinja +7 -3
- tokenizer_config.json +38 -1
chat_template.jinja
CHANGED
|
@@ -113,10 +113,12 @@
|
|
| 113 |
{%- set reasoning_content = message.reasoning_content %}
|
| 114 |
{%- endif %}
|
| 115 |
{%- set reasoning_content = reasoning_content|trim %}
|
|
|
|
|
|
|
| 116 |
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
|
| 117 |
-
{{- '<
|
| 118 |
{%- else %}
|
| 119 |
-
{{-
|
| 120 |
{%- endif %}
|
| 121 |
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 122 |
{%- for tool_call in message.tool_calls %}
|
|
@@ -143,7 +145,9 @@
|
|
| 143 |
{{- '</function>\n</tool_call>' }}
|
| 144 |
{%- endfor %}
|
| 145 |
{%- endif %}
|
| 146 |
-
{{- '<|im_end|>
|
|
|
|
|
|
|
| 147 |
{%- elif message.role == "tool" %}
|
| 148 |
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 149 |
{{- '<|im_start|>user' }}
|
|
|
|
| 113 |
{%- set reasoning_content = message.reasoning_content %}
|
| 114 |
{%- endif %}
|
| 115 |
{%- set reasoning_content = reasoning_content|trim %}
|
| 116 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 117 |
+
{%- generation %}
|
| 118 |
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
|
| 119 |
+
{{- '<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 120 |
{%- else %}
|
| 121 |
+
{{- content }}
|
| 122 |
{%- endif %}
|
| 123 |
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 124 |
{%- for tool_call in message.tool_calls %}
|
|
|
|
| 145 |
{{- '</function>\n</tool_call>' }}
|
| 146 |
{%- endfor %}
|
| 147 |
{%- endif %}
|
| 148 |
+
{{- '<|im_end|>' }}
|
| 149 |
+
{%- endgeneration %}
|
| 150 |
+
{{- '\n' }}
|
| 151 |
{%- elif message.role == "tool" %}
|
| 152 |
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 153 |
{{- '<|im_start|>user' }}
|
tokenizer_config.json
CHANGED
|
@@ -282,7 +282,6 @@
|
|
| 282 |
"<|video_pad|>"
|
| 283 |
],
|
| 284 |
"bos_token": null,
|
| 285 |
-
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n {%- endif %}\n {%- if resolved_reasoning_effort == 'xhigh' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n {%- elif resolved_reasoning_effort == 'low' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {%- if reasoning_instructions %}\n {{- reasoning_instructions + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\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 {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '') + content + '<|im_end|>\\n' }}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\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 {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\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 {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 286 |
"clean_up_tokenization_spaces": false,
|
| 287 |
"eos_token": "<|im_end|>",
|
| 288 |
"errors": "replace",
|
|
@@ -301,5 +300,43 @@
|
|
| 301 |
"video_token": "<|video_pad|>",
|
| 302 |
"vision_bos_token": "<|vision_start|>",
|
| 303 |
"vision_eos_token": "<|vision_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 304 |
}
|
| 305 |
}
|
|
|
|
| 282 |
"<|video_pad|>"
|
| 283 |
],
|
| 284 |
"bos_token": null,
|
|
|
|
| 285 |
"clean_up_tokenization_spaces": false,
|
| 286 |
"eos_token": "<|im_end|>",
|
| 287 |
"errors": "replace",
|
|
|
|
| 300 |
"video_token": "<|video_pad|>",
|
| 301 |
"vision_bos_token": "<|vision_start|>",
|
| 302 |
"vision_eos_token": "<|vision_end|>"
|
| 303 |
+
},
|
| 304 |
+
"response_template": {
|
| 305 |
+
"defaults": {
|
| 306 |
+
"role": "assistant"
|
| 307 |
+
},
|
| 308 |
+
"start_anchor": "<|im_start|>assistant\n",
|
| 309 |
+
"fields": {
|
| 310 |
+
"reasoning_content": {
|
| 311 |
+
"open": "<think>",
|
| 312 |
+
"close_pattern": "</think>|(?=<tool_call>)",
|
| 313 |
+
"content": "text"
|
| 314 |
+
},
|
| 315 |
+
"tool_calls": {
|
| 316 |
+
"open_pattern": "<tool_call>\\s*<function=(?P<name>[^>\\n]+)>",
|
| 317 |
+
"close_pattern": "</tool_call>|(?=<tool_call>)",
|
| 318 |
+
"repeats": true,
|
| 319 |
+
"content": "xml-inline",
|
| 320 |
+
"content_args": {
|
| 321 |
+
"tag_pattern": "<parameter=(?P<key>[^>\\n]+)>\\n?(?P<value>.*?)\\n?(?:</parameter>|(?=<parameter=)|(?=</function>))"
|
| 322 |
+
},
|
| 323 |
+
"transform": {
|
| 324 |
+
"type": "function",
|
| 325 |
+
"function": {
|
| 326 |
+
"name": "{name}",
|
| 327 |
+
"arguments": "{content}"
|
| 328 |
+
}
|
| 329 |
+
}
|
| 330 |
+
},
|
| 331 |
+
"content": {
|
| 332 |
+
"close": [
|
| 333 |
+
"<|im_end|>",
|
| 334 |
+
"<|endoftext|>"
|
| 335 |
+
],
|
| 336 |
+
"content": "text",
|
| 337 |
+
"repeats": true,
|
| 338 |
+
"join": ""
|
| 339 |
+
}
|
| 340 |
+
}
|
| 341 |
}
|
| 342 |
}
|