SQLV2 Q4 demo

Patrick Devaney · Intermediate ·🧠 Large Language Models ·2y ago
Demoing a 4bit quantized LLM trained towards writing SQL queries. With adequate hardware, this LLM is arguably faster and better than GPT-4 for its domain. It could help data scientists and web developers scaffold complex or repetitive sequences of queries based on natural language requests.
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Playlist UUY0xk_A4qJTQWcV2_3sqvJw · Patrick Devaney · 9 of 15

← Previous Next →

Related AI Lessons

⚡
Shared expert pool reduces parameters while maintaining performance
Learn how shared expert pools can reduce parameters in mixture-of-experts models while maintaining performance, and apply this to your own transformer architectures
Dev.to · Papers Mache
 ⚡
I Tested Claude and ChatGPT for 30 Days. Here’s My Brutally Honest Take.
Learn the brutally honest comparison of Claude and ChatGPT after a 30-day test on writing, coding, research, and daily tasks
Medium · AI
 ⚡
I Tested Claude and ChatGPT for 30 Days. Here’s My Brutally Honest Take.
Compare the capabilities of Claude and ChatGPT through a 30-day test on writing, coding, research, and daily tasks to understand their strengths and weaknesses
Medium · ChatGPT
 ⚡
Big Tech firms are accelerating AI investments and integration, while regulators and companies focus on safety and responsible adoption.
Big Tech firms are investing heavily in AI, driving growth and transformation, while emphasizing safety and responsible adoption
Dev.to AI
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →