OpenxAILabs/nix-reviewer-1.5b-GGUF

nix-reviewer-1.5b-GGUF

GGUF-format quantized builds of `OpenxAILabs/nix-reviewer-1.5b` for use with llama.cpp, Ollama, and compatible runtimes.

The full model card — training method, benchmark table, intended use, limitations — lives on the adapter repo: OpenxAILabs/nix-reviewer-1.5b.

Files

Use via Ollama

ollama pull hf.co/OpenxAILabs/nix-reviewer-1.5b-GGUF:Q4_K_M
ollama run hf.co/OpenxAILabs/nix-reviewer-1.5b-GGUF:Q4_K_M '{ pkgs, ... }:
{
  environment.systemPackages = with pkgs; [ vim vvim ];
}'

Expected output:

[{"line": 4, "severity": "error",
  "message": "`vvim` is not a nixpkgs attribute — did you mean `vim`?"}]

Use via llama.cpp

./llama-cli -m nix-reviewer-1.5b-Q4_K_M.gguf \
  --system "You are nix-assistant. Review the Nix config and output ONLY a JSON array: [{\"line\":int,\"severity\":\"error\"|\"warning\"|\"hint\",\"message\":str}]" \
  -p "{ pkgs, ... }: { environment.systemPackages = with pkgs; [ vim vvim ]; }"

System prompt (important)

The model expects this exact system prompt to emit the JSON contract:

You are nix-assistant. Review the Nix config and output ONLY a JSON array: [{"line":int,"severity":"error"|"warning"|"hint","message":str}]

Other prompts will work but output shape is less reliable.

Quantization details

• —Source: merged fp16 weights (LoRA adapter merged into base)
• —Converter: llama.cpp's convert_hf_to_gguf.py
• —Q4KM quantization: performed by Ollama's ollama create -q Q4_K_M
• —Expected quality drift vs. fp16: <3% on our benchmark (precise measurement in v0.2 release notes)

License

Apache-2.0. See LICENSE + NOTICE on the main model repo.