Instructions to use giocorte/fusion-charlie-travis 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 giocorte/fusion-charlie-travis 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 giocorte/fusion-charlie-travis:Q4_K_M # Run inference directly in the terminal: llama cli -hf giocorte/fusion-charlie-travis:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf giocorte/fusion-charlie-travis:Q4_K_M # Run inference directly in the terminal: llama cli -hf giocorte/fusion-charlie-travis:Q4_K_M
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 giocorte/fusion-charlie-travis:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf giocorte/fusion-charlie-travis:Q4_K_M
Use Docker
docker model run hf.co/giocorte/fusion-charlie-travis:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use giocorte/fusion-charlie-travis with Ollama:
ollama run hf.co/giocorte/fusion-charlie-travis:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use giocorte/fusion-charlie-travis with Docker Model Runner:
docker model run hf.co/giocorte/fusion-charlie-travis:Q4_K_M
- Lemonade
How to use giocorte/fusion-charlie-travis with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull giocorte/fusion-charlie-travis:Q4_K_M
Run and chat with the model
lemonade run user.fusion-charlie-travis-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Fusion: Charlie + Travis (single model, system-prompt conditioned)
One Qwen3-4B fine-tune that plays two characters, selected entirely by the system prompt β no special tokens, stock tokenizer.
You are Charlie, β¦β Charlie (PTSD panic NPC, inlineaction | speech)You are Travis, β¦β Travis (city-infra AI, inlineup/down | speech)
Trained with weighted SFT (action/grounding tokens up-weighted) + cross-character DPO (right-character response chosen, wrong-character rejected). Travis oversampled Γ4 to balance the mix.
Files
gguf/fusion-charlie-travis-fusion-v01.Q4_K_M-imatrix.ggufβ quantized trained model forllama-servermerged/β full 16-bit HF checkpoint (use this as the FastFlowLM / NPU input)
llama-server
llama-server -m fusion-charlie-travis-fusion-v01.Q4_K_M-imatrix.gguf
# set the system prompt to "You are Charlie, β¦" or "You are Travis, β¦"
AMD NPU (XDNA2) via FastFlowLM
Run on an AMD Ryzen AI box (NOT the training GPU):
flm convert merged/ --outfile fusion.flm
flm run fusion.flm --system "You are Charlie, β¦" --prompt "Hello"
- Downloads last month
- 9
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for giocorte/fusion-charlie-travis
Base model
Qwen/Qwen3-4B-Instruct-2507