AnishJoshi/nl2bash-custom
Viewer โข Updated โข 24.6k โข 697 โข 4
How to use SushmithaJujare/shell-buddy-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf SushmithaJujare/shell-buddy-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf SushmithaJujare/shell-buddy-GGUF:Q8_0
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf SushmithaJujare/shell-buddy-GGUF:Q8_0 # Run inference directly in the terminal: llama cli -hf SushmithaJujare/shell-buddy-GGUF:Q8_0
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf SushmithaJujare/shell-buddy-GGUF:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf SushmithaJujare/shell-buddy-GGUF:Q8_0
docker model run hf.co/SushmithaJujare/shell-buddy-GGUF:Q8_0
How to use SushmithaJujare/shell-buddy-GGUF with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SushmithaJujare/shell-buddy-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "SushmithaJujare/shell-buddy-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/SushmithaJujare/shell-buddy-GGUF:Q8_0
How to use SushmithaJujare/shell-buddy-GGUF with Ollama:
ollama run hf.co/SushmithaJujare/shell-buddy-GGUF:Q8_0
How to use SushmithaJujare/shell-buddy-GGUF with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SushmithaJujare/shell-buddy-GGUF:Q8_0
# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
"providers": {
"llama-cpp": {
"baseUrl": "http://localhost:9931/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "SushmithaJujare/shell-buddy-GGUF:Q8_0"
}
]
}
}
}# Start Pi in your project directory: pi
How to use SushmithaJujare/shell-buddy-GGUF with Docker Model Runner:
docker model run hf.co/SushmithaJujare/shell-buddy-GGUF:Q8_0
How to use SushmithaJujare/shell-buddy-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull SushmithaJujare/shell-buddy-GGUF:Q8_0
lemonade run user.shell-buddy-GGUF-Q8_0
lemonade list
How to use SushmithaJujare/shell-buddy-GGUF with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SushmithaJujare/shell-buddy-GGUF:Q8_0
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default SushmithaJujare/shell-buddy-GGUF:Q8_0
hermes
How to use SushmithaJujare/shell-buddy-GGUF with OpenClaw:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SushmithaJujare/shell-buddy-GGUF:Q8_0
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "SushmithaJujare/shell-buddy-GGUF:Q8_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
openclaw agent --local --agent main --message "Hello from Hugging Face"
A small model that turns plain English into a single Linux bash command. Fine-tuned from Qwen2.5-0.5B-Instruct and quantized to 8-bit (531 MB), so it runs on an ordinary laptop CPU.
ollama run hf.co/SushmithaJujare/shell-buddy-GGUF "find all files bigger than 1GB in my home folder"
| Model | Right tool chosen | Exact match |
|---|---|---|
| Base Qwen 0.5B (not fine-tuned) | 62% | 5% |
| Qwen 7B (14ร bigger, not fine-tuned) | 63% | 9% |
| Shell Buddy (0.5B, fine-tuned, 8-bit) | 91% | 18% |
pwd, df -h and du, because most of the training data uses find.8-bit