Instructions to use TheDrummer/Cydonia-24B-v2-GGUF 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 TheDrummer/Cydonia-24B-v2-GGUF 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 TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
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 TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
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 TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
Use Docker
docker model run hf.co/TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use TheDrummer/Cydonia-24B-v2-GGUF with Ollama:
ollama run hf.co/TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use TheDrummer/Cydonia-24B-v2-GGUF with Docker Model Runner:
docker model run hf.co/TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
- Lemonade
How to use TheDrummer/Cydonia-24B-v2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull TheDrummer/Cydonia-24B-v2-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Cydonia-24B-v2-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
it doesn't follow author notes or lorebooks
i can't seem to get the model to follow author notes or lorebooks, regardless of what depth i put
Don't go crazy with the temperature, keep it low. Temperature 0.6 + top_k 5-10 + min+p 0.1 make the model very stable for me and it listens to commands nicely, I use the author's notes and lore myself. Later you can increase the temperature, but the low temperature is very important at the beginning - reduce it even more if it does not work for you.
Example I use at depth 0-1:
[OOC: ###roleplay instructions - {{char}} don't speak or act for {{user}}.]
I also add some facts at a depth of 0-2 as the roleplay develops and the model holds on to them nicely.