Instructions to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M # Run inference directly in the terminal: llama cli -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M # Run inference directly in the terminal: llama cli -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
Use Docker
docker model run hf.co/Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix with Ollama:
ollama run hf.co/Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
- Unsloth Studio
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-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/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix to start chatting
- Pi
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix with Docker Model Runner:
docker model run hf.co/Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
- Lemonade
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
Run and chat with the model
lemonade run user.Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Lewdiculous/Captain-Eris-Diogenes_Twilight-V0.420-12B-GGUF-ARM-Imatrix:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Improving Results | Sharing prompts by a Madman
I've been away from non-Magnum models for so long that I was amazed when I managed to hit the sweet spot on this one (doing this is often difficult and stressful, apart from ruining a model totally for users), normally I'd just comment on the general discussion, but I'm here to recommend and not just share, I'll jump straight to the main point and if you want to hear more information I'll leave it to the end.
[Used]:
- [ChatML] Roleplay-V1.9 by @Virt-io (YES BOTH)
- Captain_X-Text-Completion-Preset by @Nitral-AI (ONLY THE Text-Completion™ THIS TIME)
[Results]:
- [ChatML] Roleplay-V1.9_Optimized+Physical + (Captain_X-Text-Completion-Preset_Neo)
- [ChatML] Roleplay-V1.9_Optimized+Sensual + Realistic + Physical + (Captain_X-Text-Completion-Preset_Neo)
[Explanations]:
I've been playing around a lot with Virt-io's System Prompt, trying to influence roleplays to be more “physical” or visually descriptive with bodies, that's the main reason I don't comment as much as I'd like. I'm always trying to adapt the model to my tastes however this time was special, I ended up coming across a lot of unexpected results from my research with prompts.
I noticed these prompts were more of a handicap than a benefit; and having spent a lot of time modifying some poorly-written bots, thanks to that, I stumbled across the possibility of condensing more information by optimizing words. Previously, this would have been more stupid than anything, but these days? the AIs are smarter, yet many of the prompts we have access to are either exaggerated or outdated in some way.
The first thing I did was to optimize a prompt by discarding some redundancies and condensing the size of the prompt. The problem is always complexity, in case you're wondering why certain prompts make some AIs dumber, that's it, the inability to deal with complexity, while in the end I managed to get more space for the Ai to operate, so to speak.
And of course I like physical descriptions, I'm a pervert and I won't deny it. However, the moment that made me consider this prompt worthy of sharing was when a bot took my height into account... specific? yes, for users of large models this may not seem like much, but smaller models don't usually take it into account. and Stamina, have you ever had a character that really hit fatigue? they all act like machines, and maybe that doesn't bother you, but for me? that's a pain in the ass!!
And finally, could someone test this on larger models? I'd like to know the results so I can continue my research.
Got any examples of how you set up a char card Numbra?
Got any examples of how you set up a char card Numbra?
I'm not sure I understood your question exactly; do you mean char card format, or anything related to use?
If it's related to usage, my tip is to use Guided Generations in ST (SillyTarven) to improve greetings, or to dictate the RP tone.
If it's formatting, from experience, they all work well.
If neither of the things I've commented on is what you asked, could you elaborate?