Benchmark
WikiSQL
A large-scale semantic parsing dataset used to evaluate a model's ability to convert natural language questions into SQL queries.
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%