Instructions to use FPHam/Regency-Aghast-27b-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 FPHam/Regency-Aghast-27b-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 FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O # Run inference directly in the terminal: llama cli -hf FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O # Run inference directly in the terminal: llama cli -hf FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
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 FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O # Run inference directly in the terminal: ./build/bin/llama cli -hf FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
Use Docker
docker model run hf.co/FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
- Llama new
- LM Studio
- Jan
- Ollama
How to use FPHam/Regency-Aghast-27b-GGUF with Ollama:
ollama run hf.co/FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
- Unsloth Desktop
- Docker Model Runner
How to use FPHam/Regency-Aghast-27b-GGUF with Docker Model Runner:
docker model run hf.co/FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
- Lemonade
How to use FPHam/Regency-Aghast-27b-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull FPHam/Regency-Aghast-27b-GGUF:Q4_K_M_O
Run and chat with the model
lemonade run user.Regency-Aghast-27b-GGUF-Q4_K_M_O
List all available models
lemonade list
- Atomic Chat
Development or a new persona
#1
by SandInTheDunes - opened
I wonder if this is a further development of the Regency_Bewildered_12B model or a new, distinct "persona"?
Thank you!
I kind of gathered the notes from when I was writing the book and doing it on 12b , retracted my steps and tried to apply it on 27b. I had to do some tweaks though, the 27b overfitted faster than the 12b....