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.
Finetuning LLM
Issue 13: LLM Benchmarking
The Art Of Line Scanning: Part One
RAG vs Finetuning - Your Best Approach to Boost LLM Application.
Real-World AI: LLM Tokenization - Chunking, not Clunking
Breaking Barriers: How RAG Elevates Language Model Proficiency
RAG vs Finetuning - Your Best Approach to Boost LLM Application.
Breaking Barriers: How RAG Elevates Language Model Proficiency
Breaking Barriers: How RAG Elevates Language Model Proficiency
Building a Design System for Ascend
What is the future for data scientists in a world of LLMs and
What is RAG? A simple python code with RAG like approach