Peft Fine Tuning
Skill Verifiziert AktivParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Enables efficient fine-tuning of large language models on limited hardware by training only a small fraction of parameters, offering significant memory and computational savings.
Funktionen
- Parameter-efficient fine-tuning with LoRA, QLoRA, DoRA, AdaLoRA
- Guidance on selecting optimal hyperparameters (rank, alpha)
- Support for various model architectures and target module selection
- Integration examples with TRL, Axolotl, and vLLM
- Detailed troubleshooting and best practices
Anwendungsfälle
- Fine-tuning large LLMs (7B-70B) on consumer GPUs
- Training models with minimal parameter updates (<1%) for task adaptation
- Multi-adapter serving scenarios with dynamic switching
- Memory-constrained fine-tuning using QLoRA on single GPUs
Nicht-Ziele
- Full fine-tuning of models when compute budget is not a constraint
- Training small models (<1B parameters) where full fine-tuning is more appropriate
- Providing a UI for fine-tuning; focuses on code and configuration
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Fine Tuning Expert
98Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.
PEFT Fine Tuning
96Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Unsloth
98Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Implementing Llms Litgpt
98Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
OpenVLA OFT Fine Tuning and Evaluation
98Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Axolotl Fine Tuning Skill
98Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support