README.md

LLM Reading List

General

Attention is all you need - Łukasz Kaiser

Can large language models provide useful feedback on research papers? A large-scale empirical analysis

Benchmark for evaluating code generation performance of LLMs

Systems

Llama.cpp 30B runs with only 6GB of RAM now (CPU)

Verification

LEVER: Learning to Verify Language-to-Code Generation with Execution

How Effective Are Neural Networks for Fixing Security Vulnerabilities

Courses/Tutorials

Neural Networks: Zero to Hero - A course by Andrej Karpathy on building neural networks, from scratch, in code.