A 1.5B model is a triage signal, not a verdict

说明与用途

1.5 B 模型被用作分诊信号，而非最终判决：检查在本地运行，每个输出限制为一个问题和六行上下文，延迟降至约12秒，提升透明度。

问题

Auditing trading‑strategy repositories with a 1.5B LLM is too slow for per‑file checks and produces unstable verdicts.

结果

The redesigned workflow reduces per‑finding latency to ~12 s, eliminates unstable multi‑sentence outputs, and clearly separates deterministic findings from model‑based confirmation, making the audit practical for nightly runs.

工作流

• Run deterministic checker to generate findings
• For each finding, extract evidence line + 5 surrounding lines
• Prompt local Qwen2.5‑Coder‑1.5B‑Instruct with yes/no question
• Collect model answers (YES, NO, UNSURE)
• Print report with evidence line and model verdict
• Optionally run --no‑llm for instant deterministic output

证据

The tool runs five deterministic checks over the source, then hands each finding to a local model with exactly six lines of context and one yes/no question: is this actually true here?

来源

Four model checks on the bundled sample take about 48 to 50 seconds on this laptop. That is roughly twelve seconds per question.

来源

The model never sees the repository. It sees the finding's evidence line plus five lines around it, and it can answer YES, NO, or UNSURE.

来源

The checker owns the finding. Every path:line in the report comes from code that matched a pattern.

来源