How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wallacebf/AurIA-G3-v1:F16# Run inference directly in the terminal:
llama cli -hf wallacebf/AurIA-G3-v1:F16Use 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 wallacebf/AurIA-G3-v1:F16# Run inference directly in the terminal:
./llama-cli -hf wallacebf/AurIA-G3-v1:F16Build 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 wallacebf/AurIA-G3-v1:F16# Run inference directly in the terminal:
./build/bin/llama-cli -hf wallacebf/AurIA-G3-v1:F16Use Docker
docker model run hf.co/wallacebf/AurIA-G3-v1:F16Quick Links
AurIA-G3-v1 : GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
./llama.cpp/llama-cli -hf wallacebf/AurIA-G3-v1 --jinja - For multimodal models:
./llama.cpp/llama-mtmd-cli -hf wallacebf/AurIA-G3-v1 --jinja
Available Model files:
gemma-3-4b-it-abliterated.Q8_0.ggufgemma-3-4b-it-abliterated.F16-mmproj.gguf
Note
The model's BOS token behavior was adjusted for GGUF compatibility.
This was trained 2x faster with Unsloth
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf wallacebf/AurIA-G3-v1:F16# Run inference directly in the terminal: llama cli -hf wallacebf/AurIA-G3-v1:F16