Tag
A user discusses building a small autocomplete model (25M parameters) as a learning project, mentions hardware constraints (32GB VRAM), data requirements (~100M tokens), and seeks advice on datasets and data formatting for autocomplete-style training.
This paper introduces RelGT-AC, a relational graph transformer architecture tailored for autocomplete tasks in relational databases. The model extends the RelGT architecture with column masking to prevent trivial solutions, a unified task head for multiple prediction types, and a TF-IDF text encoder to leverage lexical signals, achieving significant improvements over baselines on RelBench v2 benchmarks.
Personal update on hardware water damage recovery, showcasing MLX-VLM serving Qwen3-4B-Instruct locally on an RTX6000 Pro at ~300 tok/s for autocomplete and git commit generation via Zed IDE.
A technical guide on setting up local LLM autocomplete (Qwen2.5-Coder-7B) and agentic coding (Qwen3.6-35B-A3B) on a single 16GB GPU with 64GB+ RAM using llama.cpp, including commands and performance benchmarks.