Token Classification
GGUF
Safetensors
Chinese
input-method
zhuyin
bopomofo
traditional-chinese
ternary
bitnet
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
- llama.cpp
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
- Llama new
- LM Studio
- Jan
- Ollama
How to use Luigi/sloth-ime-models with Ollama:
ollama run hf.co/Luigi/sloth-ime-models
- Unsloth Desktop
- 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
|
Download score_vs_latency.svg from Luigi/sloth-ime-models: direct link, hf CLI and curl.
- Browser
- Download file 4.08 kB
-
https://huggingface.co/Luigi/sloth-ime-models/resolve/main/score_vs_latency.svg
- Command line
-
hf download hf://Luigi/sloth-ime-models/score_vs_latency.svg
-
curl -L -o score_vs_latency.svg https://huggingface.co/Luigi/sloth-ime-models/resolve/main/score_vs_latency.svg
4.08 kB
| <svg xmlns="http://www.w3.org/2000/svg" width="680" height="440" viewBox="0 0 680 440" font-family="-apple-system,Segoe UI,Roboto,sans-serif"> | |
| <rect x="0" y="0" width="680" height="440" rx="10" fill="#ffffff"/> | |
| <text x="74" y="26" font-size="16" font-weight="700" fill="#111827">Held-out quality vs. on-device latency (BOOX SD662)</text> | |
| <line x1="74" y1="374.0" x2="652" y2="374.0" stroke="#e5e7eb"/> | |
| <text x="64" y="378.0" font-size="12" fill="#6b7280" text-anchor="end">66</text> | |
| <line x1="74" y1="327.1" x2="652" y2="327.1" stroke="#e5e7eb"/> | |
| <text x="64" y="331.1" font-size="12" fill="#6b7280" text-anchor="end">68</text> | |
| <line x1="74" y1="280.3" x2="652" y2="280.3" stroke="#e5e7eb"/> | |
| <text x="64" y="284.3" font-size="12" fill="#6b7280" text-anchor="end">70</text> | |
| <line x1="74" y1="233.4" x2="652" y2="233.4" stroke="#e5e7eb"/> | |
| <text x="64" y="237.4" font-size="12" fill="#6b7280" text-anchor="end">72</text> | |
| <line x1="74" y1="186.6" x2="652" y2="186.6" stroke="#e5e7eb"/> | |
| <text x="64" y="190.6" font-size="12" fill="#6b7280" text-anchor="end">74</text> | |
| <line x1="74" y1="139.7" x2="652" y2="139.7" stroke="#e5e7eb"/> | |
| <text x="64" y="143.7" font-size="12" fill="#6b7280" text-anchor="end">76</text> | |
| <line x1="74" y1="92.9" x2="652" y2="92.9" stroke="#e5e7eb"/> | |
| <text x="64" y="96.9" font-size="12" fill="#6b7280" text-anchor="end">78</text> | |
| <line x1="74" y1="46.0" x2="652" y2="46.0" stroke="#e5e7eb"/> | |
| <text x="64" y="50.0" font-size="12" fill="#6b7280" text-anchor="end">80</text> | |
| <line x1="74.0" y1="46" x2="74.0" y2="374" stroke="#f3f4f6"/> | |
| <text x="74.0" y="394" font-size="12" fill="#6b7280" text-anchor="middle">8</text> | |
| <line x1="162.9" y1="46" x2="162.9" y2="374" stroke="#f3f4f6"/> | |
| <text x="162.9" y="394" font-size="12" fill="#6b7280" text-anchor="middle">9</text> | |
| <line x1="251.8" y1="46" x2="251.8" y2="374" stroke="#f3f4f6"/> | |
| <text x="251.8" y="394" font-size="12" fill="#6b7280" text-anchor="middle">10</text> | |
| <line x1="340.8" y1="46" x2="340.8" y2="374" stroke="#f3f4f6"/> | |
| <text x="340.8" y="394" font-size="12" fill="#6b7280" text-anchor="middle">11</text> | |
| <line x1="429.7" y1="46" x2="429.7" y2="374" stroke="#f3f4f6"/> | |
| <text x="429.7" y="394" font-size="12" fill="#6b7280" text-anchor="middle">12</text> | |
| <line x1="518.6" y1="46" x2="518.6" y2="374" stroke="#f3f4f6"/> | |
| <text x="518.6" y="394" font-size="12" fill="#6b7280" text-anchor="middle">13</text> | |
| <line x1="607.5" y1="46" x2="607.5" y2="374" stroke="#f3f4f6"/> | |
| <text x="607.5" y="394" font-size="12" fill="#6b7280" text-anchor="middle">14</text> | |
| <text x="363" y="426" font-size="13" fill="#374151" text-anchor="middle">latency β ms / 6-syllable decode (lower = faster)</text> | |
| <text x="18" y="210" font-size="13" fill="#374151" text-anchor="middle" transform="rotate(-90 18 210)">ε ιΈε (whole-sentence) % (higher = better)</text> | |
| <rect x="74" y="46" width="578" height="328" fill="none" stroke="#9ca3af"/> | |
| <line x1="168.3" y1="270.3" x2="162.9" y2="151.7" stroke="#dc2626" stroke-width="1.5" stroke-dasharray="4 3" opacity="0.6"/> | |
| <circle cx="168.3" cy="280.3" r="8" fill="#6b7280" stroke="#ffffff" stroke-width="2"/> | |
| <text x="168.3" y="304.3" font-size="13" font-weight="700" fill="#6b7280" text-anchor="middle">4M int8</text> | |
| <text x="168.3" y="319.3" font-size="11" fill="#6b7280" text-anchor="middle">ε 70 Β· ε83 Β· η‘74</text> | |
| <circle cx="545.3" cy="233.4" r="8" fill="#2563eb" stroke="#ffffff" stroke-width="2"/> | |
| <text x="545.3" y="203.4" font-size="13" font-weight="700" fill="#2563eb" text-anchor="middle">12M int8</text> | |
| <text x="545.3" y="219.4" font-size="11" fill="#6b7280" text-anchor="middle">ε 72 Β· ε82 Β· η‘79</text> | |
| <circle cx="162.9" cy="139.7" r="8" fill="#dc2626" stroke="#ffffff" stroke-width="2"/> | |
| <text x="162.9" y="109.7" font-size="13" font-weight="700" fill="#dc2626" text-anchor="middle">25M ternary*</text> | |
| <text x="162.9" y="125.7" font-size="11" fill="#6b7280" text-anchor="middle">ε 76 Β· ε86 Β· η‘77</text> | |
| <text x="74" y="42" font-size="11" fill="#9ca3af">* 25M ternary latency projected from measured-shape TQ2_0 / I2_S kernels</text> | |
| </svg> |