Instructions to use iito-sama/tsumukey-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 iito-sama/tsumukey-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 iito-sama/tsumukey-models:Q4_0 # Run inference directly in the terminal: llama cli -hf iito-sama/tsumukey-models:Q4_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf iito-sama/tsumukey-models:Q4_0 # Run inference directly in the terminal: llama cli -hf iito-sama/tsumukey-models:Q4_0
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 iito-sama/tsumukey-models:Q4_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf iito-sama/tsumukey-models:Q4_0
Use Docker
docker model run hf.co/iito-sama/tsumukey-models:Q4_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use iito-sama/tsumukey-models with Ollama:
ollama run hf.co/iito-sama/tsumukey-models:Q4_0
- Unsloth Desktop
- Docker Model Runner
How to use iito-sama/tsumukey-models with Docker Model Runner:
docker model run hf.co/iito-sama/tsumukey-models:Q4_0
- Lemonade
How to use iito-sama/tsumukey-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull iito-sama/tsumukey-models:Q4_0
Run and chat with the model
lemonade run user.tsumukey-models-Q4_0
List all available models
lemonade list
- Atomic Chat
Download models.json from iito-sama/tsumukey-models: direct link, hf CLI and curl.
- Browser
- Download file 846 Bytes
-
https://huggingface.co/iito-sama/tsumukey-models/resolve/main/models.json
- Command line
-
hf download hf://iito-sama/tsumukey-models/models.json
-
curl -L -o models.json https://huggingface.co/iito-sama/tsumukey-models/resolve/main/models.json
846 Bytes
| { | |
| "format": 1, | |
| "models": [ | |
| { | |
| "id": "small-r10", | |
| "kind": "ranker", | |
| "name": "Small v10 (Transformer 2L × 4H, 4.3M params)", | |
| "file": "ranker-r10.rank", | |
| "size": 4521522, | |
| "sha256": "4b1b6ccef75941ff5612f77b2c157ee7a6aba3a8ba3460f8ed63d6589959ea64", | |
| "minBuild": 26, | |
| "notes": "Round 10: corrections and next-word suggestions, en/fr/de/es, with one or two languages enabled." | |
| }, | |
| { | |
| "id": "gemma-270m-enfrdees", | |
| "kind": "gguf", | |
| "name": "Gemma 3 (Transformer 18L × 4H, 141M params)", | |
| "file": "gemma-3-270m-enfrdees64k-Q4_0.gguf", | |
| "size": 101685856, | |
| "sha256": "3290a75b1c91fd7f0a406fd135dc2bbea4f653fee939fd9fae76dd8c64c7cadf", | |
| "minBuild": 26, | |
| "notes": "Gemma 3 270M, vocabulary cut to en/fr/de/es, Q4_0. Gemma Terms of Use apply." | |
| } | |
| ] | |
| } | |