LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Open paper
Benchmark
Model
Rank
Results
music-question-answering-on-musicqa
LLaMA Adapter
#2
BLEU: 0.273
METEOR: 0.334
ROUGE: 0.413
BERT Score: 0.895
Rank counts only results with a code link.