Aller au contenu
TakoAPI
Retour aux skills

ollama-model-tuner

par gblockchainnetwork

DevOps & Cloud
436Téléchargements rapportés par clawskills.sh
1Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

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

Description

Ce que fait ce 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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

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

SORTIE

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

Prérequis

  • Ollama 0.3+ installed locally

Installation

clawhub install gblockchainnetwork/ollama-model-tuner

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens