jojo0217/korean_safe_conversation
Viewer โข Updated โข 27k โข 260 โข 59
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
# 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 cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
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 cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
docker model run hf.co/cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cookieshake/A.X-4.0-Light-Imatrix-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": "cookieshake/A.X-4.0-Light-Imatrix-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with Ollama:
ollama run hf.co/cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
"providers": {
"llama-cpp": {
"baseUrl": "http://localhost:8080/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M"
}
]
}
}
}# Start Pi in your project directory: pi
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with Docker Model Runner:
docker model run hf.co/cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
lemonade run user.A.X-4.0-Light-Imatrix-GGUF-Q4_K_M
lemonade list
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
# 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 cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
hermes
How to use cookieshake/A.X-4.0-Light-Imatrix-GGUF with OpenClaw:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "cookieshake/A.X-4.0-Light-Imatrix-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
openclaw agent --local --agent main --message "Hello from Hugging Face"
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:# Run inference directly in the terminal:
llama cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:# 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 cookieshake/A.X-4.0-Light-Imatrix-GGUF:# Run inference directly in the terminal:
./llama-cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF: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 cookieshake/A.X-4.0-Light-Imatrix-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:docker model run hf.co/cookieshake/A.X-4.0-Light-Imatrix-GGUF:for ollama version: cookieshake/a.x-4.0-light-imatrix
use template below if you are using lmstudio
{%- if tools is iterable and tools | length > 0 %}
{{- '<|im_start|><|system|>'}}
{{- '๋น์ ์ ๋๊ตฌ ํธ์ถ ๊ธฐ๋ฅ์ ๊ฐ์ถ ์ ์ฉํ ๋์ฐ๋ฏธ์
๋๋ค. ์ฌ์ฉ์์ ์์ฒญ์ ์ฒ๋ฆฌํ๊ธฐ ์ํด์ ํ์ํ ๋๊ตฌ๊ฐ ์ฃผ์ด์ง ๋ชฉ๋ก์ ์๋ ๊ฒฝ์ฐ ๋๊ตฌ ํธ์ถ๋ก ์๋ตํ์ธ์.\nํ์ํ ๋๊ตฌ๊ฐ ๋ชฉ๋ก์ ์๋ ๊ฒฝ์ฐ์๋ ๋๊ตฌ ํธ์ถ ์์ด ์ฌ์ฉ์๊ฐ ์๊ตฌํ ์ ๋ณด๋ฅผ ์ ๊ณตํ์ธ์.\nํ์ํ ๋๊ตฌ๊ฐ ๋ชฉ๋ก์ ์์ง๋ง ํด๋น ๋๊ตฌ๋ฅผ ํธ์ถํ๋๋ฐ ํ์ํ argument ์ ๋ณด๊ฐ ๋ถ์กฑํ ๊ฒฝ์ฐ ํด๋น ์ ๋ณด๋ฅผ ์ฌ์ฉ์์๊ฒ ์์ฒญํ์ธ์.\n์ฌ์ฉ์์ ์์ฒญ์ ์ฒ๋ฆฌํ๊ธฐ ์ํด ์ฌ๋ฌ๋ฒ ๋๊ตฌ๋ฅผ ํธ์ถํ ์ ์์ด์ผ ํฉ๋๋ค.\n๋๊ตฌ ํธ์ถ ์ดํ ๋๊ตฌ ์คํ ๊ฒฐ๊ณผ๋ฅผ ์
๋ ฅ์ผ๋ก ๋ฐ์ผ๋ฉด ํด๋น ๊ฒฐ๊ณผ๋ฅผ ํ์ฉํ์ฌ ๋ต๋ณ์ ์์ฑํ์ธ์.\n\n๋ค์์ ์ ๊ทผํ ์ ์๋ ๋๊ตฌ๋ค์ ๋ชฉ๋ก ์
๋๋ค:\n<tools>\n' }}
{%- for t in tools %}
{{- t | tojson }}
{{- '\n' }}
{%- endfor %}
{{- '</tools>' }}
{{- '\n\n๋๊ตฌ๋ฅผ ํธ์ถํ๋ ค๋ฉด ์๋์ JSON์ผ๋ก ์๋ตํ์ธ์.\n๋๊ตฌ ํธ์ถ ํ์: <tool_call>{"name": ๋๊ตฌ ์ด๋ฆ, "arguments": dictionary ํํ์ ๋๊ตฌ ์ธ์๊ฐ}</tool_call>' }}
{{- '<|im_end|>' }}
{%- endif %}
{%- for message in messages %}
{%- if message.role == 'system' %}
{{- '<|im_start|><|system|>' + message.content + '<|im_end|>'}}
{%- elif message.role == 'user' %}
{{- '<|im_start|><|user|>' + message.content + '<|im_end|>'}}
{%- elif message.role == 'assistant' %}
{{- '<|im_start|><|assistant|>'}}
{%- set content = '' %}
{%- if message.content is defined %}
{%- set content = message.content %}
{%- endif %}
{%- if add_generation_prompt and not (message.reasoning_content is defined and message.reasoning_content is not none) %}
{%- if '</think>' in message.content %}
{%- set content = (message.content.split('</think>') | last).lstrip('\n') %}
{%- endif %}
{%- endif %}
{{- content}}
{%- if message.tool_calls is defined %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{#-- ์์ ์ : 'do' ๊ตฌ๋ฌธ์ ์ฌ์ฉํ์ง ์๋๋ก if/else๋ก ๋ก์ง์ ๋ณ๊ฒฝ --#}
{%- if tool_call.arguments is defined and tool_call.arguments %}
{%- set tc_data = {"name": tool_call.name, "arguments": tool_call.arguments} %}
{%- else %}
{%- set tc_data = {"name": tool_call.name} %}
{%- endif %}
{{- '<tool_call>' + (tc_data | tojson) + '</tool_call>' -}}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>'}}
{%- elif message.role == 'tool' %}
{{- '<|im_start|><|extra_id_13|><tool_output>' + message.content + '</tool_output><|im_end|>'}}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|><|assistant|>' }}
{%- endif %}
1-bit
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Base model
skt/A.X-4.0-Light
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:# Run inference directly in the terminal: llama cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF: