Open Issues Need Help
View All on GitHub enhancement good first issue
deathsamsul/finetune-vs-rag-benchmark deathsamsul/finetune-vs-rag-benchmark A reproducible benchmark comparing LLM fine-tuning (LoRA/QLoRA), RAG, and Fine-tuning + RAG across answer quality, faithfulness, latency, robustness, and failure modes.
Open project →
0
A reproducible benchmark comparing LLM fine-tuning (LoRA/QLoRA), RAG, and Fine-tuning + RAG across answer quality, faithfulness, latency, robustness, and failure modes.
Python