LLM Fine-tuning and LoRA Optimization
15 repos
Fine-tuning and parameter-efficient adaptation techniques for large language models, with heavy emphasis on LoRA (Low-Rank Adaptation) and related methods. This cluster covers frameworks and tools for training customized LLM variants—from multi-GPU orchestration systems like OmniTune and LoRA-MCL to complete training pipelines like OneTrainer and specialized implementations for models like Llama and Alpaca. Most repos are Python-based PyTorch implementations focused on making fine-tuning accessible and scalable.
Python · 14
C · 1
fine-tuning ·7,492
lora ·7,476
llm ·3,904
reinforcement-learning ·3,497
meta-learning ·3,495
metaclaw ·3,495
agent ·3,495
continual-learning ·3,495
ai-agent ·3,495
online-learning ·3,495
