Image-Text-to-Text
Transformers
Safetensors
qwen3_5_moe
qwen3.6
nvfp4
quantized
abliterated
uncensored
vllm
compressed-tensors
blackwell
Mixture of Experts
multimodal
agentic
claude
opus
conversational
Instructions to use sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4") 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("sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4") model = AutoModelForMultimodalLM.from_pretrained("sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4", 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 sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4", "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/sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4
- SGLang
How to use sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4 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 "sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4" \ --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": "sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4", "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 "sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4" \ --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": "sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4", "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 sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4 with Docker Model Runner:
docker model run hf.co/sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-NVFP4
| {%- set image_count = namespace(value=0) -%} | |
| {%- set video_count = namespace(value=0) -%} | |
| {%- set ns = namespace(enable_thinking=true, multi_step_tool=true, last_query_index=messages|length - 1) -%} | |
| {#- | |
| Patched Qwen3.6 chat template for coding-agent/tool-calling use. | |
| This is a conservative drop-in patch for Qwen3.6-family repos. It preserves the | |
| official Qwen3.6 vision/text rendering and XML-like tool-call syntax, while fixing | |
| common coding-agent issues around developer messages, thinking toggles, historical | |
| tool calls, and tool responses. | |
| Key changes from the official Qwen3.6 template: | |
| - Preserve image/video/text content handling from upstream Qwen3.6. | |
| - Fold consecutive leading system/developer messages into one system block. | |
| - Support <|think_on|> / <|think_off|> and the enable_thinking flag. | |
| - Avoid exposing thinking-toggle control tokens to the model. | |
| - Avoid injecting empty historical <think> blocks unless generation is explicitly think-off. | |
| - Serialize assistant.tool_calls safely for mapping arguments and JSON-string arguments. | |
| - Include Function: <name> in tool responses when available. | |
| -#} | |
| {%- 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/developer 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/developer 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 %} | |
| {%- macro process_thinking_toggles(content) %} | |
| {%- if '<|think_off|>' in content %} | |
| {%- set ns.enable_thinking = false %} | |
| {{- content | replace('<|think_off|>', '') | trim }} | |
| {%- elif '<|think_on|>' in content %} | |
| {%- set ns.enable_thinking = true %} | |
| {{- content | replace('<|think_on|>', '') | trim }} | |
| {%- else %} | |
| {{- content | trim }} | |
| {%- endif %} | |
| {%- endmacro %} | |
| {%- if enable_thinking is defined and enable_thinking is false %} | |
| {%- set ns.enable_thinking = false %} | |
| {%- endif %} | |
| {%- if not messages %} | |
| {{- raise_exception('No messages provided.') }} | |
| {%- endif %} | |
| {#- Fold consecutive leading system/developer messages into one system block. -#} | |
| {%- set leading = namespace(content='', end_index=0) %} | |
| {%- for message in messages %} | |
| {%- if loop.index0 == leading.end_index and (message.role == 'system' or message.role == 'developer') %} | |
| {%- set content = render_content(message.content, false, true) %} | |
| {%- set content = process_thinking_toggles(content) %} | |
| {%- if content %} | |
| {%- if leading.content %} | |
| {%- set leading.content = leading.content + '\n\n' + content %} | |
| {%- else %} | |
| {%- set leading.content = content %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set leading.end_index = loop.index0 + 1 %} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- 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 leading.content %} | |
| {{- '\n\n' + leading.content }} | |
| {%- endif %} | |
| {{- '<|im_end|>\n' }} | |
| {%- else %} | |
| {%- if leading.content %} | |
| {{- '<|im_start|>system\n' + leading.content + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |
| {#- Find the last real user query. Trailing tool-response user blocks are part of multi-step tool use. -#} | |
| {%- 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 loop.index0 < leading.end_index %} | |
| {#- Already rendered in the leading system block. -#} | |
| {%- elif message.role == "system" or message.role == "developer" %} | |
| {{- raise_exception('System/developer messages must be consecutive and at the beginning.') }} | |
| {%- elif message.role == "user" %} | |
| {%- set content = process_thinking_toggles(content) %} | |
| {{- '<|im_start|>user\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 %} | |
| {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} | |
| {%- set content = content.split('</think>')[-1].lstrip('\n') %} | |
| {%- elif '</thinking>' in content %} | |
| {%- set reasoning_content = content.split('</thinking>')[0].rstrip('\n').split('<thinking>')[-1].lstrip('\n') %} | |
| {%- set content = content.split('</thinking>')[-1].lstrip('\n') %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set reasoning_content = reasoning_content | trim %} | |
| {{- '<|im_start|>assistant\n' }} | |
| {%- if reasoning_content and loop.index0 > ns.last_query_index %} | |
| {{- '<think>\n' + reasoning_content + '\n</think>\n\n' }} | |
| {%- endif %} | |
| {{- content }} | |
| {%- 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 %} | |
| {%- 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 %} | |
| {%- set t_args = tool_call.arguments %} | |
| {%- if t_args is mapping %} | |
| {%- for args_name, args_value in t_args | items %} | |
| {{- '<parameter=' + args_name + '>\n' }} | |
| {%- set args_value = args_value | string if args_value is string else args_value | tojson %} | |
| {{- args_value }} | |
| {{- '\n</parameter>\n' }} | |
| {%- endfor %} | |
| {%- elif t_args is string %} | |
| {{- '<parameter=arguments>\n' }} | |
| {{- t_args }} | |
| {{- '\n</parameter>\n' }} | |
| {%- else %} | |
| {{- '<parameter=arguments>\n' }} | |
| {{- t_args | tojson }} | |
| {{- '\n</parameter>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |
| {{- '</function>\n</tool_call>' }} | |
| {%- endfor %} | |
| {%- endif %} | |
| {{- '<|im_end|>\n' }} | |
| {%- elif message.role == "tool" %} | |
| {%- if loop.index0 == 0 or messages[loop.index0 - 1].role != "tool" %} | |
| {{- '<|im_start|>user' }} | |
| {%- endif %} | |
| {{- '\n<tool_response>\n' }} | |
| {%- if message.name is defined and message.name %} | |
| {{- 'Function: ' + message.name + '\n' }} | |
| {%- endif %} | |
| {{- content }} | |
| {{- '\n</tool_response>' }} | |
| {%- if loop.last or messages[loop.index0 + 1].role != "tool" %} | |
| {{- '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- else %} | |
| {{- raise_exception('Unexpected message role.') }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- if add_generation_prompt %} | |
| {{- '<|im_start|>assistant\n' }} | |
| {%- if ns.enable_thinking %} | |
| {{- '<think>\n' }} | |
| {%- else %} | |
| {{- '<think>\n\n</think>\n\n' }} | |
| {%- endif %} | |
| {%- endif %} | |