Instructions to use arxhr007/lxask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arxhr007/lxask with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use arxhr007/lxask 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 arxhr007/lxask:Q4_K_M # Run inference directly in the terminal: llama cli -hf arxhr007/lxask:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf arxhr007/lxask:Q4_K_M # Run inference directly in the terminal: llama cli -hf arxhr007/lxask:Q4_K_M
Build from source code
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 arxhr007/lxask:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf arxhr007/lxask:Q4_K_M
Use Docker
docker model run hf.co/arxhr007/lxask:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use arxhr007/lxask with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "arxhr007/lxask" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arxhr007/lxask", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/arxhr007/lxask:Q4_K_M
- Ollama
How to use arxhr007/lxask with Ollama:
ollama run hf.co/arxhr007/lxask:Q4_K_M
- Unsloth Desktop
- Pi
How to use arxhr007/lxask with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf arxhr007/lxask:Q4_K_M
Configure the model in Pi
# 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": "arxhr007/lxask:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use arxhr007/lxask with Docker Model Runner:
docker model run hf.co/arxhr007/lxask:Q4_K_M
- Lemonade
How to use arxhr007/lxask with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull arxhr007/lxask:Q4_K_M
Run and chat with the model
lemonade run user.lxask-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use arxhr007/lxask with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf arxhr007/lxask:Q4_K_M
Configure Hermes
# 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 arxhr007/lxask:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use arxhr007/lxask with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf arxhr007/lxask:Q4_K_M
Configure OpenClaw
# 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 "arxhr007/lxask:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf arxhr007/lxask:Q4_K_M# Run inference directly in the terminal:
llama cli -hf arxhr007/lxask:Q4_K_MBuild from source code
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 arxhr007/lxask:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama cli -hf arxhr007/lxask:Q4_K_MUse Docker
docker model run hf.co/arxhr007/lxask:Q4_K_Mlxask β offline Linux command assistant
A 1.5B model fine-tuned to turn plain-English requests into Linux commands. Runs on CPU in about 1.3 GB of memory β no GPU, no cloud, no API key β and ships with two small LoRA adapters it routes between per request.
Built for lxask, a Rust + llama.cpp CLI that wraps the model with retrieval from the real man pages/tldr corpus, answer checks, and a rule that it never executes a command for you.
Files
| file | what |
|---|---|
lxask-round4-Q4_K_M.gguf |
the fine-tuned model, Q4_K_M (~986 MB) |
restrict-round4.gguf |
llama.cpp LoRA adapter: ruled-out programs ("without lsof") and proxy contexts |
precision-round4.gguf |
llama.cpp LoRA adapter: near-miss discipline β exact filenames, quoting, right flag, leaves keep-files alone |
adapters/restrict/ |
the same adapter in PEFT safetensors format (rank 16) |
adapters/precision/ |
the same adapter in PEFT safetensors format (rank 16) |
The adapters are routed, not stacked: restriction/proxy questions get
restrict, everything else gets precision. Both GGUF adapters apply to the
quantized model directly in llama.cpp.
Measured (held-out sets, commands executed in a sandbox)
- Strict execution success on generated file/text tasks: 35.0% β 73.8% with the precision adapter (160 tasks)
- NL2SH-ALFA public benchmark (300 tasks, Docker harness, reward 1.0 only): 62% vs 54% for the untuned Qwen2.5-Coder-1.5B under its strongest prompting (McNemar p = 0.003)
- Right program on everyday questions: 96β99%; restrictions kept on programs never ruled out in training: 76%
Training
Qwen2.5-Coder-1.5B β SFT on ~39k examples (tldr-pages, NL2Bash, generated
requests checked by a validator) β GRPO with commands actually executed in a
sandbox as the reward β two rank-16 LoRA adapters trained on contrastive tasks
(hard negatives that look right but do the wrong job), each proven to pass
reference fixtures and fail no-op/negative variants before training.
Use
Simplest: install lxask β it loads these files for you.
curl -fsSLO https://github.com/arxhr007/lxask/releases/latest/download/install.sh
sh install.sh
lxask "count the words in report.txt" # β wc --words report.txt
Or drive the GGUFs with llama.cpp directly (--lora for an adapter), or load
the PEFT adapters onto Qwen/Qwen2.5-Coder-1.5B in transformers.
Limits
A 1.5B model gets details wrong sometimes β wrong awk field, wrong uniq
sign, occasionally a documentation placeholder left in a path. The companion
CLI exists to catch that: it checks every answer against the documentation and
marks what it cannot verify. Read the command before you run it.
- Downloads last month
- 135
4-bit
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf arxhr007/lxask:Q4_K_M# Run inference directly in the terminal: llama cli -hf arxhr007/lxask:Q4_K_M