hridya423/lexis-1.5b-GGUF

lexis-1.5b

Plain English in, one shell command out, for macOS, Linux and Windows. This is the default local model for Lexis, a terminal assistant that shows every command on an approval card before it runs.

It is a full fine-tune of Qwen2.5-Coder-1.5B-Instruct on 138,977 requests whose commands were each checked on their target OS. The file is Q4_K_M, 986 MB, and answers in about 250 ms on an Apple M4 Pro.

	macOS	Linux	Windows	All
Final held-out set, first try	265 / 337	284 / 332	208 / 250	757 / 919 (82.4%)

For comparison, lexis-0.5b scores 714 / 919 at 398 MB and about 100 ms. METHODOLOGY.md covers the data, the checks, the evaluation, and the experiments that didn't help.

Use it through Lexis

curl -fsSL https://lexis.hridya.tech/install.sh | bash   # macOS, Linux
irm https://lexis.hridya.tech/win.ps1 | iex              # Windows
lx "biggest 10 files in my Downloads"

The installer downloads this model, sets up llama.cpp, and asks before running anything that changes your system.

Use it directly

The model expects exactly the prompt it was trained on: a fixed system prompt, then the request with a platform line appended.

llama-server -m lexis-1.5b-q4_k_m.gguf --jinja -c 4096 --port 8080

curl -s localhost:8080/v1/chat/completions -d '{
  "temperature": 0,
  "messages": [
    {"role": "system", "content": "You are a bash command generator. Given a natural language request, output only the bash command that accomplishes it. No explanation, no markdown fences."},
    {"role": "user", "content": "find all pdfs on my desktop\n(Platform: macOS (BSD), shell: zsh)"}
  ]}' | jq -r '.choices[0].message.content'

Platform lines used in training:

• (Platform: macOS (BSD), shell: zsh)
• (Platform: Linux (GNU), shell: bash)
• (Platform: windows, shell: powershell), with this system prompt instead: You are a PowerShell command generator. Given a natural language request, output only the PowerShell command that accomplishes it. No explanation, no markdown fences.

To fix a failed command, use You fix broken bash commands. Given a failed command and its error output, output only the corrected command. No explanation. as the system prompt. The user message is the command after $ , then the error output on the following lines, with no platform line.

Limits

• One command per answer, no explanation. Multi-step tasks come back joined with && or ;.
• About one first-try answer in six is wrong. Typical mistakes are a rarer tool it doesn't know, an invented flag, or a missed detail such as sort order or case sensitivity.
• It does what it's asked, including destructive things. It has no safety judgment of its own and will occasionally answer a harmless question with something drastic. Don't execute its output without a review step; Lexis provides one.