Instructions to use giocorte/fusion-charlie-travis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giocorte/fusion-charlie-travis with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="giocorte/fusion-charlie-travis",
	filename="gguf/fusion-charlie-travis-fusion-v01.Q4_K_M-imatrix.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

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

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 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/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 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

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 Studio

How to use giocorte/fusion-charlie-travis 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 giocorte/fusion-charlie-travis 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 giocorte/fusion-charlie-travis to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for giocorte/fusion-charlie-travis to start chatting

Atomic Chat new
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

Fusion: Charlie + Travis (single model, system-prompt conditioned)

One Qwen3-4B fine-tune that plays two characters, selected entirely by the system prompt — no special tokens, stock tokenizer.

You are Charlie, … → Charlie (PTSD panic NPC, inline action | speech)
You are Travis, … → Travis (city-infra AI, inline up/down | speech)

Trained with weighted SFT (action/grounding tokens up-weighted) + cross-character DPO (right-character response chosen, wrong-character rejected). Travis oversampled ×4 to balance the mix.

Files

gguf/fusion-charlie-travis-fusion-v01.Q4_K_M-imatrix.gguf — quantized trained model for llama-server
merged/ — 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, …" or "You are Travis, …"

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, …" --prompt "Hello"

Downloads last month: 42

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for giocorte/fusion-charlie-travis

Base model

Qwen/Qwen3-4B-Instruct-2507

Quantized

(267)

this model