LaunchKit · 2026
Back to Skills

ollama-model-tuner

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

0
436 downloads
by @gblockchainnetwork

Setup & Installation

openclaw skills install @gblockchainnetwork/ollama-model-tuner

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install ollama-model-tuner

What This Skill Does

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.

When to use it

  • 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

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

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

AGENT
  1. 1Load JSONL dataset from ./data.json
  2. 2Run scripts/tune.py with --model llama3 and --task classification
  3. 3Apply prompt templates from prompts/system.md
  4. 4Execute eval loop and record accuracy metrics
  5. 5Output tuned Modelfile and benchmark report
OUTPUT

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

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Ollama 0.3+ installed locally