Instructions to use Luigi/sloth-ime-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Luigi/sloth-ime-models 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 Luigi/sloth-ime-models
# Run inference directly in the terminal:
llama cli -hf Luigi/sloth-ime-models

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Luigi/sloth-ime-models
# Run inference directly in the terminal:
llama cli -hf Luigi/sloth-ime-models

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 Luigi/sloth-ime-models
# Run inference directly in the terminal:
./llama-cli -hf Luigi/sloth-ime-models

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 Luigi/sloth-ime-models
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Luigi/sloth-ime-models

Use Docker

docker model run hf.co/Luigi/sloth-ime-models

LM Studio
Jan
Ollama
How to use Luigi/sloth-ime-models with Ollama:
```
ollama run hf.co/Luigi/sloth-ime-models
```

Unsloth Studio

How to use Luigi/sloth-ime-models 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 Luigi/sloth-ime-models 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 Luigi/sloth-ime-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Luigi/sloth-ime-models to start chatting

Docker Model Runner
How to use Luigi/sloth-ime-models with Docker Model Runner:
```
docker model run hf.co/Luigi/sloth-ime-models
```

Lemonade

How to use Luigi/sloth-ime-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Luigi/sloth-ime-models

Run and chat with the model

lemonade run user.sloth-ime-models-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

sloth-ime-models / .gitattributes

Commit History

add 60M Q4 next-word predictor (qwen35 GDN hybrid, 47.3/75.8 held-out, 8.5ms/word on BOOX @4t )

7913d33
verified

Luigi commited on 20 days ago

add 12M ternary 256x12 sibling (9.65MB TQ2_0, 84%/84%, 9.3ms@4t on BOOX)

f46ccb0
verified

Luigi commited on 20 days ago

SlothE-T 25M ternary Zhuyin→zh-TW IME model: ternary GGUF (TQ2_0) + fp32 master + reproducibility toolchain

f0f7133
verified

Luigi commited on 25 days ago

initial commit

d8ae2df
verified

Luigi commited on 25 days ago

Commit History

add 60M Q4 next-word predictor (qwen35 GDN hybrid, 47.3/75.8 held-out, 8.5ms/word on BOOX @4t ) 7913d33 verified

add 12M ternary 256x12 sibling (9.65MB TQ2_0, 84%/84%, 9.3ms@4t on BOOX) f46ccb0 verified

SlothE-T 25M ternary Zhuyin→zh-TW IME model: ternary GGUF (TQ2_0) + fp32 master + reproducibility toolchain f0f7133 verified

initial commit d8ae2df verified

add 60M Q4 next-word predictor (qwen35 GDN hybrid, 47.3/75.8 held-out, 8.5ms/word on BOOX @4t )

7913d33
verified

add 12M ternary 256x12 sibling (9.65MB TQ2_0, 84%/84%, 9.3ms@4t on BOOX)

f46ccb0
verified

SlothE-T 25M ternary Zhuyin→zh-TW IME model: ternary GGUF (TQ2_0) + fp32 master + reproducibility toolchain

f0f7133
verified

initial commit

d8ae2df
verified