There are two main approaches to improving the performance of large language models (LLMs) on specific tasks: finetuning and retrieval-based generation. Finetuning involves updating the weights of an LLM that has been pre-trained on a large corpus of text and code.
What is RAG? A simple python code with RAG like approach
Finetuning LLM
RAG vs Finetuning - Your Best Approach to Boost LLM Application.
Issue 13: LLM Benchmarking
Issue 24: The Algorithms behind the magic
50 excellent ChatGPT prompts specifically tailored for programmers
Controlling Packets on the Wire: Moving from Strength to Domination
Accelerating technological changes - Holodeck by Midjourney CEO
Language Embeddings
MedPaLM vs ChatGPT - First do no harm