LuthorSQL gates text-to-SQL locally before a slower LLM agent
The 7B model scores 68.03% execution accuracy on BIRD’s hidden test at 0.84 seconds per question on one GPU.
1 stories, newest first · one card per story
The 7B model scores 68.03% execution accuracy on BIRD’s hidden test at 0.84 seconds per question on one GPU.
Today 1K readers · 1.2K views · 172 reads · all time 202K views