본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

ollama-model-tuner

gblockchainnetwork 제작

DevOps & Cloud
436clawskills.sh가 보고한 다운로드 수
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Optimize Ollama models/prompts using local datasets, eval metrics, and iterative tuning.

설명

이 스킬이 하는 일

Tunes Ollama models locally using custom datasets, prompt engineering, and LoRA fine-tuning. Supports A/B testing prompts, customizing Modelfiles, and benchmarking model performance against eval metrics. No cloud services or external APIs required.

Runs the entire tuning loop on local hardware, so sensitive training data never leaves the machine and there are no per-token API costs.

사용 시점

  • Fine-tuning a local llama3 model for document classification
  • A/B testing system prompts to find the best performer for a chatbot
  • Adding a LoRA adapter trained on company-specific terminology
  • Benchmarking response quality before and after Modelfile changes
  • Iterating on prompt templates using a local JSONL eval dataset

예시 워크플로

입력

User asks: tune llama3 on my support ticket dataset for intent classification

에이전트
  1. 1

    Load JSONL dataset from ./data.json

  2. 2

    Run scripts/tune.py with --model llama3 and --task classification

  3. 3

    Apply prompt templates from prompts/system.md

  4. 4

    Execute eval loop and record accuracy metrics

  5. 5

    Output tuned Modelfile and benchmark report

출력

Fine-tuned Modelfile with updated system prompt and eval metrics summary

요구 사항

  • Ollama 0.3+ installed locally

설치

clawhub install gblockchainnetwork/ollama-model-tuner

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크