Text Generation
GGUF
imatrix
conversational
How to use from
llama.cpp
Install (macOS, Linux)
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:
# Run inference directly in the terminal:
llama cli -hf cookieshake/A.X-4.0-Light-Imatrix-GGUF:
Install from WinGet (Windows)
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:
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 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:
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 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:
Use Docker
docker model run hf.co/cookieshake/A.X-4.0-Light-Imatrix-GGUF:
Quick Links

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 ํ˜ธ์ถœ ๊ธฐ๋Šฅ์„ ๊ฐ–์ถ˜ ์œ ์šฉํ•œ ๋„์šฐ๋ฏธ์ž…๋‹ˆ๋‹ค. ์‚ฌ์šฉ์ž์˜ ์š”์ฒญ์„ ์ฒ˜๋ฆฌํ•˜๊ธฐ ์œ„ํ•ด์„œ ํ•„์š”ํ•œ ๋„๊ตฌ๊ฐ€ ์ฃผ์–ด์ง„ ๋ชฉ๋ก์— ์žˆ๋Š” ๊ฒฝ์šฐ ๋„๊ตฌ ํ˜ธ์ถœ๋กœ ์‘๋‹ตํ•˜์„ธ์š”.\nํ•„์š”ํ•œ ๋„๊ตฌ๊ฐ€ ๋ชฉ๋ก์— ์—†๋Š” ๊ฒฝ์šฐ์—๋Š” ๋„๊ตฌ ํ˜ธ์ถœ ์—†์ด ์‚ฌ์šฉ์ž๊ฐ€ ์š”๊ตฌํ•œ ์ •๋ณด๋ฅผ ์ œ๊ณตํ•˜์„ธ์š”.\nํ•„์š”ํ•œ ๋„๊ตฌ๊ฐ€ ๋ชฉ๋ก์— ์žˆ์ง€๋งŒ ํ•ด๋‹น ๋„๊ตฌ๋ฅผ ํ˜ธ์ถœํ•˜๋Š”๋ฐ ํ•„์š”ํ•œ argument ์ •๋ณด๊ฐ€ ๋ถ€์กฑํ•œ ๊ฒฝ์šฐ ํ•ด๋‹น ์ •๋ณด๋ฅผ ์‚ฌ์šฉ์ž์—๊ฒŒ ์š”์ฒญํ•˜์„ธ์š”.\n์‚ฌ์šฉ์ž์˜ ์š”์ฒญ์„ ์ฒ˜๋ฆฌํ•˜๊ธฐ ์œ„ํ•ด ์—ฌ๋Ÿฌ๋ฒˆ ๋„๊ตฌ๋ฅผ ํ˜ธ์ถœํ•  ์ˆ˜ ์žˆ์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.\n๋„๊ตฌ ํ˜ธ์ถœ ์ดํ›„ ๋„๊ตฌ ์‹คํ–‰ ๊ฒฐ๊ณผ๋ฅผ ์ž…๋ ฅ์œผ๋กœ ๋ฐ›์œผ๋ฉด ํ•ด๋‹น ๊ฒฐ๊ณผ๋ฅผ ํ™œ์šฉํ•˜์—ฌ ๋‹ต๋ณ€์„ ์ƒ์„ฑํ•˜์„ธ์š”.\n\n๋‹ค์Œ์€ ์ ‘๊ทผํ•  ์ˆ˜ ์žˆ๋Š” ๋„๊ตฌ๋“ค์˜ ๋ชฉ๋ก ์ž…๋‹ˆ๋‹ค:\n<tools>\n' }}
    {%- for t in tools %}
        {{- t | tojson }}
        {{- '\n' }}
    {%- endfor %}
    {{- '</tools>' }}
    {{- '\n\n๋„๊ตฌ๋ฅผ ํ˜ธ์ถœํ•˜๋ ค๋ฉด ์•„๋ž˜์˜ JSON์œผ๋กœ ์‘๋‹ตํ•˜์„ธ์š”.\n๋„๊ตฌ ํ˜ธ์ถœ ํ˜•์‹: <tool_call>{"name": ๋„๊ตฌ ์ด๋ฆ„, "arguments": dictionary ํ˜•ํƒœ์˜ ๋„๊ตฌ ์ธ์ž๊ฐ’}</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 %}
                
                {#-- ์ˆ˜์ •์ : 'do' ๊ตฌ๋ฌธ์„ ์‚ฌ์šฉํ•˜์ง€ ์•Š๋„๋ก if/else๋กœ ๋กœ์ง์„ ๋ณ€๊ฒฝ --#}
                {%- 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 %}
Downloads last month
395
GGUF
Model size
7B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for cookieshake/A.X-4.0-Light-Imatrix-GGUF

Quantized
(15)
this model

Dataset used to train cookieshake/A.X-4.0-Light-Imatrix-GGUF