Benchmark
MultiNLI
The Multi-Genre Natural Language Inference corpus, used to evaluate model performance on natural language inference tasks.
Timeline (last 90 days)
Oct 16
LoRA performs comparably to or even better than full fine-tuning on RoBERTa, DeBERTa, GPT-2 and GPT-3, for example reaching 74.0% on WikiSQL and 91.7% on MultiNLI.
Unverified50%