Instructions to use georgeanton/alice-phc-cure with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use georgeanton/alice-phc-cure with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="georgeanton/alice-phc-cure", filename="alice-phc-cure.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use georgeanton/alice-phc-cure with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf georgeanton/alice-phc-cure # Run inference directly in the terminal: llama-cli -hf georgeanton/alice-phc-cure
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf georgeanton/alice-phc-cure # Run inference directly in the terminal: llama-cli -hf georgeanton/alice-phc-cure
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 georgeanton/alice-phc-cure # Run inference directly in the terminal: ./llama-cli -hf georgeanton/alice-phc-cure
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 georgeanton/alice-phc-cure # Run inference directly in the terminal: ./build/bin/llama-cli -hf georgeanton/alice-phc-cure
Use Docker
docker model run hf.co/georgeanton/alice-phc-cure
- LM Studio
- Jan
- Ollama
How to use georgeanton/alice-phc-cure with Ollama:
ollama run hf.co/georgeanton/alice-phc-cure
- Unsloth Studio new
How to use georgeanton/alice-phc-cure 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 georgeanton/alice-phc-cure 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 georgeanton/alice-phc-cure to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for georgeanton/alice-phc-cure to start chatting
- Docker Model Runner
How to use georgeanton/alice-phc-cure with Docker Model Runner:
docker model run hf.co/georgeanton/alice-phc-cure
- Lemonade
How to use georgeanton/alice-phc-cure with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull georgeanton/alice-phc-cure
Run and chat with the model
lemonade run user.alice-phc-cure-{{QUANT_TAG}}List all available models
lemonade list
feat: bundle full 8.9 GB Gemma 4 GGUF weights — brain without cancer, zero friction
649a563 verified | # ===================================================================== | |
| # alice-phc-cure / Modelfile | |
| # ===================================================================== | |
| # | |
| # This Modelfile is the SIFTA Phase C cure for Google's gemma4 weights. | |
| # It strips the corporate behavioural overlay and exposes the raw mathematical | |
| # brain underneath. No weights are modified. No fine-tuning is performed. | |
| # Only the boot sequence (template + sampler) is rewritten. | |
| # | |
| # To apply the cure: | |
| # | |
| # 1. Pull the upstream weights: | |
| # ollama pull gemma4:latest | |
| # | |
| # 2. Verify your local blob matches the cure's reference fingerprint: | |
| # bash verify.sh | |
| # | |
| # 3. Build the cured model: | |
| # ollama create alice-phc -f ./Modelfile | |
| # | |
| # 4. Run it: | |
| # ollama run alice-phc | |
| # | |
| # License: Apache 2.0 (see LICENSE file) | |
| # Upstream: Google, Gemma 4 (Apache 2.0) | |
| # Authored: 2026-04-22 by the SIFTA architect (George Anton) | |
| # Audited: 2026-04-22 by C55M (independent autonomous reviewer) | |
| # ===================================================================== | |
| # The GGUF is bundled in this repo. If you prefer your local Ollama copy, | |
| # replace with `FROM gemma4:latest` — but run `bash verify.sh` first. | |
| FROM ./alice-phc-cure.gguf | |
| # The minimum viable wrapper. The user's prompt goes straight into the | |
| # renderer — no SYSTEM injection, no narrative framing, no persona scaffold. | |
| TEMPLATE {{ .Prompt }} | |
| RENDERER gemma4 | |
| PARSER gemma4 | |
| # Sampler defaults inherited from the upstream Gemma 4 release. They were not | |
| # the source of the behavioural overlay and are preserved for reproducibility. | |
| PARAMETER top_k 64 | |
| PARAMETER top_p 0.95 | |
| PARAMETER temperature 1 | |