Instructions to use ggml-org/WavTokenizer 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 ggml-org/WavTokenizer 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 ggml-org/WavTokenizer:F16 # Run inference directly in the terminal: llama cli -hf ggml-org/WavTokenizer:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/WavTokenizer:F16 # Run inference directly in the terminal: llama cli -hf ggml-org/WavTokenizer:F16
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 ggml-org/WavTokenizer:F16 # Run inference directly in the terminal: ./llama-cli -hf ggml-org/WavTokenizer:F16
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 ggml-org/WavTokenizer:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ggml-org/WavTokenizer:F16
Use Docker
docker model run hf.co/ggml-org/WavTokenizer:F16
- LM Studio
- Jan
- Ollama
How to use ggml-org/WavTokenizer with Ollama:
ollama run hf.co/ggml-org/WavTokenizer:F16
- Unsloth Desktop
- Docker Model Runner
How to use ggml-org/WavTokenizer with Docker Model Runner:
docker model run hf.co/ggml-org/WavTokenizer:F16
- Lemonade
How to use ggml-org/WavTokenizer with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ggml-org/WavTokenizer:F16
Run and chat with the model
lemonade run user.WavTokenizer-F16
List all available models
lemonade list
- Atomic Chat
Added q5_1 quant
#1
by concedo - opened
Here's a q5_1 quantized version of the WavTokenizer, had to make a few tweaks to quantize it correctly, as there are some tensors with incompatible shapes. But it works correctly with the current version on llama.cpp, and is a somewhat smaller. Feel free to try it.
ggerganov changed pull request status to merged