A 1.5B model fine-tuned to turn plain-English requests into Linux commands. Runs on CPU in about 1.3 GB of memory — no GPU, no cloud, no API key — 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.
| 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 — 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.
Qwen2.5-Coder-1.5B → SFT on ~39k examples (tldr-pages, NL2Bash, generated
requests checked by a validator) → GRPO with commands actually executed in a
sandbox as the reward → 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.
Simplest: install lxask — 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" # → 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.
A 1.5B model gets details wrong sometimes — 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.
Qwen/Qwen2.5-Coder-1.5B