Text Generation
PyTorch
ONNX
Safetensors
GGUF
Italian
lumina_next
lumina
coding
italian
long-context
rope
yarn
gqa
Instructions to use jacopof/lumina 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 jacopof/lumina 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 jacopof/lumina # Run inference directly in the terminal: llama cli -hf jacopof/lumina
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf jacopof/lumina # Run inference directly in the terminal: llama cli -hf jacopof/lumina
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 jacopof/lumina # Run inference directly in the terminal: ./build/bin/llama cli -hf jacopof/lumina
Use Docker
docker model run hf.co/jacopof/lumina
- Llama new
- LM Studio
- Jan
- vLLM
How to use jacopof/lumina with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jacopof/lumina" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jacopof/lumina", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jacopof/lumina
- Ollama
How to use jacopof/lumina with Ollama:
ollama run hf.co/jacopof/lumina
- Unsloth Desktop
- Docker Model Runner
How to use jacopof/lumina with Docker Model Runner:
docker model run hf.co/jacopof/lumina
- Lemonade
How to use jacopof/lumina with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull jacopof/lumina
Run and chat with the model
lemonade run user.lumina-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download weights.json from jacopof/lumina: direct link, hf CLI and curl.
- Browser
- Download file 57.9 MB
-
https://huggingface.co/jacopof/lumina/resolve/main/weights.json
- Command line
-
hf download hf://jacopof/lumina/weights.json
-
curl -L -o weights.json https://huggingface.co/jacopof/lumina/resolve/main/weights.json
57.9 MB
- Xet hash:
- 71083a835af4d0a0d7d17118a0ce34da3e235652254cc08f1c7cf588b6334241
- Size of remote file:
- 57.9 MB
- SHA256:
- bdaa8b9e398d0da575128fab925ea190ec5ce21cd43b75bc9b60197818f9c25a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.