Instructions to use ggml-org/vocabs 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/vocabs 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/vocabs # Run inference directly in the terminal: llama cli -hf ggml-org/vocabs
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ggml-org/vocabs # Run inference directly in the terminal: llama cli -hf ggml-org/vocabs
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/vocabs # Run inference directly in the terminal: ./llama-cli -hf ggml-org/vocabs
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/vocabs # Run inference directly in the terminal: ./build/bin/llama-cli -hf ggml-org/vocabs
Use Docker
docker model run hf.co/ggml-org/vocabs
- Llama new
- LM Studio
- Jan
- Ollama
How to use ggml-org/vocabs with Ollama:
ollama run hf.co/ggml-org/vocabs
- Unsloth Desktop
- Docker Model Runner
How to use ggml-org/vocabs with Docker Model Runner:
docker model run hf.co/ggml-org/vocabs
- Lemonade
How to use ggml-org/vocabs with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ggml-org/vocabs
Run and chat with the model
lemonade run user.vocabs-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
gpt-oss and Tekken test vocabs
#2
by tkrane2 - opened
This is for #30787. The Tekken files include Thai and Hindi strings. Both cases do not pass on the master but pass with the fix. They merge together with the llama.cpp PR, and the files are in a new BPE/ folder.
CISCai changed pull request status to open
CISCai changed pull request status to merged
CISCai deleted the
refs/pr/2 ref