Vai al contenuto
TakoAPI
Torna alle skill

ollama-model-tuner

di gblockchainnetwork

DevOps & Cloud
436Download riportati da clawskills.sh
1Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

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

Descrizione

Cosa fa questa skill

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.

Quando usarla

  • 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

Esempio di workflow

INPUT

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

AGENT
  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

OUTPUT

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

Requisiti

  • Ollama 0.3+ installed locally

Installazione

clawhub install gblockchainnetwork/ollama-model-tuner

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link