Llama Factory
Skill Verified ActiveExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
To empower users to efficiently fine-tune LLMs with LLaMA-Factory through expert guidance, a no-code WebUI, and comprehensive documentation, enabling advanced model customization without deep coding.
Features
- No-code WebUI for LLM fine-tuning
- Support for 100+ models including LLaMA, LLaVA, Mistral, Qwen, Gemma
- Various fine-tuning techniques: LoRA, QLoRA (2-8 bit), full parameter tuning
- Comprehensive documentation covering installation, usage, advanced features, and troubleshooting
- Support for NPU training and inference
Use Cases
- Fine-tuning LLMs with custom datasets using LLaMA-Factory's WebUI
- Implementing advanced fine-tuning strategies like QLoRA or LoRA+
- Setting up and running inference with fine-tuned models
- Understanding and configuring distributed training for large models
Non-Goals
- Providing a standalone LLM inference service
- Implementing novel LLM architectures
- Offering a platform for model hosting or deployment beyond configuration guidance
Installation
First, add the marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Llama Factory
96Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Implementing Llms Litgpt
100Implements 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.
Unsloth
100Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Ray Train
99Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
Huggingface Accelerate
99Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
OpenPI Fine Tuning and Serving
98Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.