Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Locally fine-tune Ollama models, prompts, and LoRAs using custom datasets and evaluation metrics without requiring cloud resources.
Locally fine-tune Ollama models, prompts, and LoRAs using custom datasets and evaluation metrics without requiring cloud resources.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Prompt engineering & A/B testing Modelfile customization LoRA fine-tuning with local data Performance benchmarking
!ollama-model-tuner --model llama3 --dataset ./data.json --task classification
scripts/tune.py: Python tuner with eval loop prompts/system.md: Base system prompts
Ollama 0.3+, Python 3.10+, datasets in JSONL/CSV.
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.