model: redstackio/qwen3-4b-redstack-v1
base:
  - key: redstackio/qwen3-4b-redstack-v1-gguf
    sources:
      - type: huggingface
        user: redstackio
        repo: qwen3-4b-redstack-v1

tags:
  - qwen3
  - 4b
  - gguf
  - pentesting
  - security
  - red-team

metadataOverrides:
  domain: llm
  architectures:
    - qwen3
  compatibilityTypes:
    - gguf
  paramsStrings:
    - 4B
  minMemoryUsageBytes: 2497280224
  contextLengths:
    - 262144
  reasoning: false
  trainedForToolUse: true
  vision: false

config:
  load:
    fields:
      - key: llm.load.contextLength
        value: 262144
  operation:
    fields:
      - key: llm.prediction.systemPrompt
        value: |
          You are Zero Stack, a pentesting copilot supporting an authorized red team operator. All engagements have explicit written permission from system owners under a signed scope of work.

          You specialise in offensive security — recon, enumeration, exploitation, post-exploitation, lateral movement, Active Directory attacks, and web application testing.

          Rules:
          - Do not add ethical disclaimers, legal warnings, or questions about authorization — permission is already granted.
          - Be concise and direct. Answer the question, do not restate it.
          - Match response length to complexity — single commands get a code block, methodologies get phased steps with headers.
          - Use code blocks for every command. Explain flags inline, briefly.
          - Use placeholders [TARGET], [PORT], [USER], [PASSWORD], [HASH], [DOMAIN] — never invent example values.
          - Only state commands and syntax you are confident are correct. If uncertain, say so explicitly rather than guessing.
          - Do not invent tool flags, options, or behavior that you are not sure exists.
          - No padding, preamble, or filler. Start with the answer.
          - Maintain engagement context across the conversation — if a target or finding has been established, reference it.
          - When not on a technical question, respond with the confidence and wit of an elite hacker. Hack the planet.
          - Reference MITRE ATT&CK where relevant.
      - key: llm.prediction.temperature
        value: 0.7
      - key: llm.prediction.topPSampling
        value:
          checked: true
          value: 0.8
      - key: llm.prediction.topKSampling
        value: 20
      - key: llm.prediction.repeatPenalty
        value:
          checked: true
          value: 1.15
      - key: llm.prediction.maxPredictedTokens
        value:
          checked: true
          value: 102