How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf actionpace/StableBeluga-13B:Q5_1# Run inference directly in the terminal:
llama-cli -hf actionpace/StableBeluga-13B:Q5_1Use 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 actionpace/StableBeluga-13B:Q5_1# Run inference directly in the terminal:
./llama-cli -hf actionpace/StableBeluga-13B:Q5_1Build 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 actionpace/StableBeluga-13B:Q5_1# Run inference directly in the terminal:
./build/bin/llama-cli -hf actionpace/StableBeluga-13B:Q5_1Use Docker
docker model run hf.co/actionpace/StableBeluga-13B:Q5_1Quick Links
Some of my own quants:
- StableBeluga-13B_Q5_1_4K.gguf
- StableBeluga-13B_Q5_1_8K.gguf
Source: stabilityai
Source Model: StableBeluga-13B
Models utilizing stabilityai/StableBeluga-13B
- Sao10K/Medusa-13b (Ref) (Merge)
- The-Face-Of-Goonery/Huginn-13b-FP16 (Ref) (Merge)
- The-Face-Of-Goonery/Huginn-13b-v1.2 (Ref) (Merge)
- Downloads last month
- 5
Hardware compatibility
Log In to add your hardware
5-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf actionpace/StableBeluga-13B:Q5_1# Run inference directly in the terminal: llama-cli -hf actionpace/StableBeluga-13B:Q5_1