Image-Text-to-Text
Transformers
Safetensors
qwen3_5
heretic
uncensored
decensored
abliterated
mpoa
conversational
4-bit precision
gptq
Instructions to use llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4") 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, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4") model = AutoModelForImageTextToText.from_pretrained("llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4") 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 llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4", "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/llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4
- SGLang
How to use llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4 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 "llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4" \ --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": "llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4", "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 "llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4" \ --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": "llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4", "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 llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4 with Docker Model Runner:
docker model run hf.co/llmfan46/Qwen3.6-27B-uncensored-heretic-v2-GPTQ-Int4
Upload chat_template.jinja
Browse files- chat_template.jinja +222 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id is defined and add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id is defined and add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- set ns_flags = namespace(enable_thinking=true) %}
|
| 43 |
+
{%- if enable_thinking is defined %}
|
| 44 |
+
{%- set ns_flags.enable_thinking = enable_thinking %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{%- set preserve_thinking = preserve_thinking | default(true) %}
|
| 47 |
+
{%- if not messages %}
|
| 48 |
+
{{- raise_exception('No messages provided.') }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- if add_generation_prompt is defined and add_generation_prompt and continue_final_message is defined and continue_final_message %}
|
| 51 |
+
{{- raise_exception('add_generation_prompt and continue_final_message cannot both be true.') }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 54 |
+
{{- '<|im_start|>system\n' }}
|
| 55 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 56 |
+
{%- for tool in tools %}
|
| 57 |
+
{{- "\n" }}
|
| 58 |
+
{{- tool | tojson }}
|
| 59 |
+
{%- endfor %}
|
| 60 |
+
{{- "\n</tools>" }}
|
| 61 |
+
{{- '\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>' }}
|
| 62 |
+
{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{%- if '<|think_off|>' in content %}
|
| 65 |
+
{%- set ns_flags.enable_thinking = false %}
|
| 66 |
+
{%- set content = content.replace('<|think_off|>', '') %}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- if '<|think_on|>' in content %}
|
| 69 |
+
{%- set ns_flags.enable_thinking = true %}
|
| 70 |
+
{%- set content = content.replace('<|think_on|>', '') %}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{%- set content = content.strip() %}
|
| 73 |
+
{%- if content %}
|
| 74 |
+
{{- '\n\n' + content }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{{- '<|im_end|>\n' }}
|
| 78 |
+
{%- else %}
|
| 79 |
+
{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
|
| 80 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 81 |
+
{%- if '<|think_off|>' in content %}
|
| 82 |
+
{%- set ns_flags.enable_thinking = false %}
|
| 83 |
+
{%- set content = content.replace('<|think_off|>', '') %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- if '<|think_on|>' in content %}
|
| 86 |
+
{%- set ns_flags.enable_thinking = true %}
|
| 87 |
+
{%- set content = content.replace('<|think_on|>', '') %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- set content = content.strip() %}
|
| 90 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{%- endif %}
|
| 93 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 94 |
+
{%- for message in messages[::-1] %}
|
| 95 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 96 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 97 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 98 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 99 |
+
{%- set ns.multi_step_tool = false %}
|
| 100 |
+
{%- set ns.last_query_index = index %}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{%- endfor %}
|
| 104 |
+
{%- if ns.multi_step_tool %}
|
| 105 |
+
{%- set ns.last_query_index = messages|length - 1 %}
|
| 106 |
+
{%- endif %}
|
| 107 |
+
{%- for message in messages %}
|
| 108 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 109 |
+
{%- set content = content.replace('<|think_off|>', '').replace('<|think_on|>', '') %}
|
| 110 |
+
{%- set content = content.strip() %}
|
| 111 |
+
{%- if message.role == "system" or message.role == "developer" %}
|
| 112 |
+
{%- if not loop.first %}
|
| 113 |
+
{%- set sys_content = render_content(message.content, false, true)|trim %}
|
| 114 |
+
{%- set sys_content = sys_content.replace('<|think_off|>', '').replace('<|think_on|>', '')|trim %}
|
| 115 |
+
{{- '<|im_start|>system\n' + sys_content + '<|im_end|>' + '\n' }}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- elif message.role == "user" %}
|
| 118 |
+
{{- '<|im_start|>' + message.role + '\n' + (content if content else ' ') + '<|im_end|>' + '\n' }}
|
| 119 |
+
{%- elif message.role == "assistant" %}
|
| 120 |
+
{%- set reasoning_content = '' %}
|
| 121 |
+
{%- if message.reasoning_content is string %}
|
| 122 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 123 |
+
{%- else %}
|
| 124 |
+
{%- set has_think_tag = false %}
|
| 125 |
+
{%- set think_start_token = '<think>' %}
|
| 126 |
+
{%- set think_end_token = '</think>' %}
|
| 127 |
+
{%- if '</think>' in content %}
|
| 128 |
+
{%- set has_think_tag = true %}
|
| 129 |
+
{%- elif '</thinking>' in content %}
|
| 130 |
+
{%- set has_think_tag = true %}
|
| 131 |
+
{%- set think_start_token = '<thinking>' %}
|
| 132 |
+
{%- set think_end_token = '</thinking>' %}
|
| 133 |
+
{%- elif '<think>' in content %}
|
| 134 |
+
{%- set reasoning_content = content.split('<think>')[-1].lstrip('\n') %}
|
| 135 |
+
{%- set content = '' %}
|
| 136 |
+
{%- elif '<thinking>' in content %}
|
| 137 |
+
{%- set reasoning_content = content.split('<thinking>')[-1].lstrip('\n') %}
|
| 138 |
+
{%- set content = '' %}
|
| 139 |
+
{%- endif %}
|
| 140 |
+
{%- if has_think_tag %}
|
| 141 |
+
{%- set reasoning_content = content.split(think_end_token)[0].rstrip('\n').split(think_start_token)[-1].lstrip('\n') %}
|
| 142 |
+
{%- set content = content.split(think_end_token)[-1].lstrip('\n') %}
|
| 143 |
+
{%- endif %}
|
| 144 |
+
{%- endif %}
|
| 145 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 146 |
+
{%- set show_think = false %}
|
| 147 |
+
{%- if loop.index0 > ns.last_query_index and reasoning_content|length > 0 %}
|
| 148 |
+
{%- set show_think = true %}
|
| 149 |
+
{%- elif ns_flags.enable_thinking and preserve_thinking and reasoning_content|length > 0 %}
|
| 150 |
+
{%- set show_think = true %}
|
| 151 |
+
{%- endif %}
|
| 152 |
+
{%- if show_think %}
|
| 153 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 154 |
+
{%- else %}
|
| 155 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 156 |
+
{%- endif %}
|
| 157 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 158 |
+
{%- for tool_call in message.tool_calls %}
|
| 159 |
+
{%- if tool_call.function is defined %}
|
| 160 |
+
{%- set tool_call = tool_call.function %}
|
| 161 |
+
{%- endif %}
|
| 162 |
+
{%- if loop.first %}
|
| 163 |
+
{%- if content|trim %}
|
| 164 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 165 |
+
{%- else %}
|
| 166 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 167 |
+
{%- endif %}
|
| 168 |
+
{%- else %}
|
| 169 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 170 |
+
{%- endif %}
|
| 171 |
+
{%- if tool_call.arguments is defined and tool_call.arguments is mapping %}
|
| 172 |
+
{%- if tool_call.arguments|length > 0 %}
|
| 173 |
+
{%- for args_name in tool_call.arguments %}
|
| 174 |
+
{%- set args_value = tool_call.arguments[args_name] %}
|
| 175 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 176 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson %}
|
| 177 |
+
{{- args_value }}
|
| 178 |
+
{{- '\n</parameter>\n' }}
|
| 179 |
+
{%- endfor %}
|
| 180 |
+
{%- endif %}
|
| 181 |
+
{%- elif tool_call.arguments is defined and tool_call.arguments is string %}
|
| 182 |
+
{%- if tool_call.arguments|trim|length > 0 %}
|
| 183 |
+
{#- Note: raw JSON string arguments are emitted as-is and will not match
|
| 184 |
+
the XML parameter format in the tool instructions. Normalize arguments
|
| 185 |
+
to a dict in your serving layer before applying this template. -#}
|
| 186 |
+
{{- tool_call.arguments }}
|
| 187 |
+
{{- '\n' }}
|
| 188 |
+
{%- endif %}
|
| 189 |
+
{%- endif %}
|
| 190 |
+
{{- '</function>\n</tool_call>' }}
|
| 191 |
+
{%- endfor %}
|
| 192 |
+
{%- endif %}
|
| 193 |
+
{%- if not (loop.last and continue_final_message is defined and continue_final_message is true) %}
|
| 194 |
+
{{- '<|im_end|>\n' }}
|
| 195 |
+
{%- endif %}
|
| 196 |
+
{%- elif message.role == "tool" %}
|
| 197 |
+
{%- if not loop.previtem or (loop.previtem.role != "tool" and loop.previtem.role != "assistant") %}
|
| 198 |
+
{{- raise_exception('A tool message must follow an assistant or tool message.') }}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 201 |
+
{{- '<|im_start|>user' }}
|
| 202 |
+
{%- endif %}
|
| 203 |
+
{{- '\n<tool_response>\n' }}
|
| 204 |
+
{{- content }}
|
| 205 |
+
{{- '\n</tool_response>' }}
|
| 206 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 207 |
+
{{- '<|im_end|>\n' }}
|
| 208 |
+
{%- elif loop.last %}
|
| 209 |
+
{{- '<|im_end|>\n' }}
|
| 210 |
+
{%- endif %}
|
| 211 |
+
{%- else %}
|
| 212 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 213 |
+
{%- endif %}
|
| 214 |
+
{%- endfor %}
|
| 215 |
+
{%- if add_generation_prompt %}
|
| 216 |
+
{{- '<|im_start|>assistant\n' }}
|
| 217 |
+
{%- if ns_flags.enable_thinking is false %}
|
| 218 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 219 |
+
{%- else %}
|
| 220 |
+
{{- '<think>\n' }}
|
| 221 |
+
{%- endif %}
|
| 222 |
+
{%- endif %}
|