Instructions to use Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix 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 Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix 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 Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: llama cli -hf Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: llama cli -hf Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix: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 Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix: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 Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M
Use Docker
docker model run hf.co/Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix with Ollama:
ollama run hf.co/Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M
- Unsloth Studio
How to use Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix to start chatting
- Docker Model Runner
How to use Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix with Docker Model Runner:
docker model run hf.co/Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M
- Lemonade
How to use Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix:Q4_K_M
Run and chat with the model
lemonade run user.llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix-Q4_K_M
List all available models
lemonade list
- Atomic Chat
General feedback and issue report.
Ooo I Immediately added to the list and will wait for iq3 to test it, thank you for quants!
@woofwolfy - Oki! IQ3 quants are up!
It's interesting, but the model is very fond of purple prose and even follows instructions too well, I mean she's too sensitive to the cues in the message examples. Anyway, to me this model reminded me of Lemonade but much better and with its own features where you have to customize some things. Otherwise, formatting works without fail.
Follows instructions very well, particularly in dictating style and formatting. This model is really well suited toward serving as a game master for more open scenes as opposed to specific characters (though it does those well, also).
Works incredibly well on machines with low processing power. It follows the prompt's storyline very well and has perfect instruction following for its intended use. I highly recommend everyone to at least try it, as I was pleasantly surprised by this model in all the cards I used it for and the generated responses.
Hi, I started using this model the Q4 KM version. I am having an issue when using chat mode for role play. Frequently the model will summarize the recent events and analyze them and make suggestions. Also it even decided it wanted to switch characters and for the model to act as "me" and for me to act as the model. Also sometimes it will write a normal response and then write a response for me. How do I stop this? Thank you in advance.