Instructions to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF") 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 AutoModel model = AutoModel.from_pretrained("huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF", dtype="auto") - llama-cpp-python
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF", filename="Q3_K-GGUF/Q3_K-GGUF-00001-of-00021.gguf", )
llm.create_chat_completion( 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" } } ] } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16 # Run inference directly in the terminal: llama-cli -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16 # Run inference directly in the terminal: llama-cli -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16 # Run inference directly in the terminal: ./llama-cli -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Use Docker
docker model run hf.co/huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
- LM Studio
- Jan
- vLLM
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF", "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/huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
- SGLang
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF 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 "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF" \ --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": "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF", "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 "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF" \ --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": "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF", "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" } } ] } ] }' - Ollama
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Ollama:
ollama run hf.co/huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
- Unsloth Studio
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF to start chatting
- Pi
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Docker Model Runner:
docker model run hf.co/huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
- Lemonade
How to use huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull huihui-ai/Huihui-Qwen3.5-397B-A17B-abliterated-GGUF:F16
Run and chat with the model
lemonade run user.Huihui-Qwen3.5-397B-A17B-abliterated-GGUF-F16
List all available models
lemonade list
Upload chat_template-vl-think.jinja
Browse files- chat_template-vl-think.jinja +115 -0
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if do_vision_count %}
|
| 10 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 13 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 14 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 15 |
+
{%- if do_vision_count %}
|
| 16 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 19 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 20 |
+
{%- elif 'text' in item %}
|
| 21 |
+
{{- item.text }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- endfor %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- endmacro %}
|
| 26 |
+
{%- if tools %}
|
| 27 |
+
{{- '<|im_start|>system\n' }}
|
| 28 |
+
{%- if messages[0].role == 'system' %}
|
| 29 |
+
{{- render_content(messages[0].content, false) + '\n\n' }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 32 |
+
{%- for tool in tools %}
|
| 33 |
+
{{- "\n" }}
|
| 34 |
+
{{- tool | tojson }}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if messages[0].role == 'system' %}
|
| 39 |
+
{{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 43 |
+
{%- for message in messages[::-1] %}
|
| 44 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 45 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 46 |
+
{%- set content = render_content(message.content, false) %}
|
| 47 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 48 |
+
{%- set ns.multi_step_tool = false %}
|
| 49 |
+
{%- set ns.last_query_index = index %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- endfor %}
|
| 53 |
+
{%- for message in messages %}
|
| 54 |
+
{%- set content = render_content(message.content, True) %}
|
| 55 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 56 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 57 |
+
{%- elif message.role == "assistant" %}
|
| 58 |
+
{%- set reasoning_content = '' %}
|
| 59 |
+
{%- if message.reasoning_content is string %}
|
| 60 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if '</think>' in content %}
|
| 63 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 64 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 68 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 69 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- else %}
|
| 74 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- if message.tool_calls %}
|
| 77 |
+
{%- for tool_call in message.tool_calls %}
|
| 78 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 79 |
+
{{- '\n' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- if tool_call.function %}
|
| 82 |
+
{%- set tool_call = tool_call.function %}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 85 |
+
{{- tool_call.name }}
|
| 86 |
+
{{- '", "arguments": ' }}
|
| 87 |
+
{%- if tool_call.arguments is string %}
|
| 88 |
+
{{- tool_call.arguments }}
|
| 89 |
+
{%- else %}
|
| 90 |
+
{{- tool_call.arguments | tojson }}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{{- '}\n</tool_call>' }}
|
| 93 |
+
{%- endfor %}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{{- '<|im_end|>\n' }}
|
| 96 |
+
{%- elif message.role == "tool" %}
|
| 97 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 98 |
+
{{- '<|im_start|>user' }}
|
| 99 |
+
{%- endif %}
|
| 100 |
+
{{- '\n<tool_response>\n' }}
|
| 101 |
+
{{- content }}
|
| 102 |
+
{{- '\n</tool_response>' }}
|
| 103 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 104 |
+
{{- '<|im_end|>\n' }}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- endif %}
|
| 107 |
+
{%- endfor %}
|
| 108 |
+
{%- if add_generation_prompt %}
|
| 109 |
+
{{- '<|im_start|>assistant\n' }}
|
| 110 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 111 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 112 |
+
{%- else %}
|
| 113 |
+
{{- '<think>\n' }}
|
| 114 |
+
{%- endif %}
|
| 115 |
+
{%- endif %}
|