All skills
finetuning
Adapts open-weight models to a tone or output format using LoRA, QLoRA and preference optimization.
- Part of ericrisco/rsc-harness
- 7 installs
- Machine Learning · Fine-tuning and quantization
More Fine-tuning and quantization skills
See all- agent-platform-tuning10kFine-tunes open and Gemini models using Agent Platform infrastructure.
- agent-platform-tuning-management9.9kLists, inspects and cancels ongoing model tuning jobs in Agent Platform.
- fine-tuning-expert4.6kHelps fine-tune language models with LoRA adapters, training datasets, hyperparameters and deployment.
- ruview-model-training25Trains, fine-tunes and publishes RuView pose and embedding models, including GPU training and Hugging Face uploads.
Also in this pack
- game-design20Designs or repairs game fun: mechanics, loops, progression, economy, difficulty and prototyping.
- deep-learning11Trains and debugs PyTorch neural networks, covering training loops, mixed precision, and distributed setups.
- level-design10Designs a game level's layout, pacing, player guidance, encounter progression and secret placement.
- machine-learning10Builds classic tabular prediction models with scikit-learn, XGBoost or LightGBM and leak-free validation.