LLM Fine-tuning and Parameter Efficiency
9 repos
Techniques and tools for adapting large language models through efficient fine-tuning methods like LoRA and QLoRA, which reduce memory and computational requirements compared to full model training. The cluster covers practical implementations for popular models (Llama, Gemma) and frameworks that make parameter-efficient adaptation accessible. Repositories here range from research-oriented adaptations to production-ready runners and optimization utilities.
Python · 9
fine-tuning ·415
lora ·401
llm ·396
qlora ·256
caveman ·242
unsloth ·242
style-transfer ·242
gemma ·242
deep-learning ·135
chatgpt ·135
