Instructions to use leeyunjai/themaker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use leeyunjai/themaker with 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 leeyunjai/themaker # Run inference directly in the terminal: llama cli -hf leeyunjai/themaker
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf leeyunjai/themaker # Run inference directly in the terminal: llama cli -hf leeyunjai/themaker
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf leeyunjai/themaker # Run inference directly in the terminal: ./build/bin/llama cli -hf leeyunjai/themaker
Use Docker
docker model run hf.co/leeyunjai/themaker
- Llama new
- LM Studio
- Jan
- Ollama
How to use leeyunjai/themaker with Ollama:
ollama run hf.co/leeyunjai/themaker
- Unsloth Desktop
- Docker Model Runner
How to use leeyunjai/themaker with Docker Model Runner:
docker model run hf.co/leeyunjai/themaker
- Lemonade
How to use leeyunjai/themaker with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull leeyunjai/themaker
Run and chat with the model
lemonade run user.themaker-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
themaker ๊ธฐ๊ธฐ ๋ชจ๋ธ ๋ชจ์ (ํ์ด๋ณดยทํ์ด๋ธ๋ ์ธ)
๋ก๋ด์ /home/pi/.model ์ ๊ทธ๋๋ก ๋ค์ด๊ฐ๋ ๋ชจ๋ธ ๋ฌถ์์
๋๋ค. ๋ก๋ด์ ์คํ๋ผ์ธ์ผ๋ก ๋๊ธฐ ๋๋ฌธ์ ์ด ํด๋๋ฅผ ๋ฏธ๋ฆฌ ๋ฃ์ด ๋ก๋๋ค.
huggingface-cli download leeyunjai/themaker --include ".model/*" --local-dir /home/pi
cd /home/pi/.model && sed -n '/^## sha256/,$p' VERSION | tail -n +2 | sha256sum -c --quiet && echo ๊ฐ์
- ํ์ผ๋ง๋ค sha256 ์
.model/VERSION์ ์์ต๋๋ค. ๋ฐ์ ๋ค ์ ๋ช ๋ น์ผ๋ก ๋์กฐํฉ๋๋ค. git clone๋์huggingface-cli download๋ฅผ ์๋๋ค(clone ์.git/lfs์ ํ ๋ฒ์ ๋ ๋จ๊น๋๋ค).
.model/llm โ ๋ํ ๋ชจ๋ธ
ํ์ผ ์ด๋ฆ์ ๋ชจ๋ธ ์ด๋ฆ ๊ทธ๋๋ก์
๋๋ค(๋งํฌ ์๋). ์ด๋ ํ์ธ์ง๋ VERSION ์ llm/<์ด๋ฆ>.gguf = โฆ ์ค์ ์ ์ต๋๋ค.
| ํ์ผ | ์๋ ํ | ๋ด์ฉ | ๋ผ์ด์ ์ค | sha256 |
|---|---|---|---|---|
| general.gguf | gemma-3-1b-it-Q4_K_M | Google Gemma 3 1B IT | Gemma Terms of Use | 8270790f3ab69fdfe860b7b64008d9a19986d8df7e407bb018184caa08798ebd |
| themaker-ko.gguf | themaker-0.8b-Q4_K_M | ์ํ๋ฌ์ค ๊ต์ก์ฉ AI ๋๋ฉ์ด์ปค, ํ๊ตญ์ด (Qwen3.5-0.8B ๋ฏธ์ธ์กฐ์ ) | Apache-2.0 (๋ฐํ ๋ชจ๋ธ) | 2a8799ec40d2f9a3facc035d7ab7eabc0fcc61b5e5637d7ddbb9ea453b21970c |
| themaker-en.gguf | themaker-en-0.8b-Q4_K_M | ์ํ๋ฌ์ค ๊ต์ก์ฉ AI ๋๋ฉ์ด์ปค, ์์ด (Qwen3.5-0.8B ๋ฏธ์ธ์กฐ์ ) | Apache-2.0 (๋ฐํ ๋ชจ๋ธ) | 39bf09302eb91777f7b4e9909feafc41ce13e1b183a5e7efff5afaceabca1570 |
์คํ: llama-server@<์ด๋ฆ> (llama.cpp b11889, --ctx-size 2048)
๊ทธ ๋ฐ์ ํด๋
| ํด๋ | ๋ด์ฉ | ๋ผ์ด์ ์ค |
|---|---|---|
| tts/ | Supertonic 3 int8 ๋ณํ๋ณธ(vocoder ๋ง fp32), ๋ชฉ์๋ฆฌ F1 |
OpenRAIL-M (LICENSE-OpenRAIL-M.txt, ๋ณํ ๊ณ ์ง MODIFICATIONS.md) |
| stt/ | SenseVoiceSmall int8 (sherpa-onnx ๋ณํ) + silero_vad.onnx | FunASR ๋ชจ๋ธ ๋ผ์ด์ ์ค (LICENSE-SenseVoice) / MIT |
| object/ | easydetect ed-s COCO 80 (ed-s-320.onnx) | Apache-2.0 |
| face/ | OpenVINO Open Model Zoo 2023.0 FP16 โ face-detection-retail-0005 ยท age-gender-recognition-retail-0013 ยท emotions-recognition-retail-0003 ยท face-reidentification-retail-0095, MediaPipe face_landmarker.task | Apache-2.0 |
| hand/ | MediaPipe gesture_recognizer.task ยท rps_recognizer.task | Apache-2.0 |
| mask/ | ๋ง์คํฌ ํ๋ณ mask.onnx (edge-lab, ์๋ฒ ๋ + ๋ถ๋ฅ๊ธฐ ํ ๊ฐ) | Apache-2.0 |
๊ณ ์ง
- themaker ๋ชจ๋ธ์ ํ๊ตญ์ง๋ฅ์ ๋ณด์ฌํ์งํฅ์์ ์ฌ์ ๊ฒฐ๊ณผ์ธ AI Hub ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ํ์ตํ์์ต๋๋ค.
- Qwen3.5-0.8B: Apache License 2.0, Copyright Alibaba Cloud.
- Gemma 3 is provided under and subject to the Gemma Terms of Use found at https://ai.google.dev/gemma/terms
- ๊ทธ ๋ฐ์ ๋ชจ๋ธ์ ๊ฐ ํด๋์ LICENSE๋ฅผ ๋ฐ๋ฆ ๋๋ค.
- Downloads last month
- 557
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support