An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"
The source of LMSYS website and blogs
The code and data for the GPT-4 based benchmark in the vicuna blog post