FastChat vs. Guanaco

Overview

FastChat is the open platform for training, serving, and evaluating LLM chatbots developed and maintained by LMSYS.

FastChat is an open-source library for training, serving, and evaluating LLM chat systems from LMSYS. It includes training and evaluation code, a model serving system, a Web GUI, and a finetuning pipeline, and is the de facto system for Vicuna as well as FastChat-T5. FastChat also includes the Chatbot Arena for benchmarking LLMs.

Initial release: 2023-04-28

Reference

https://github.com/lm-sys/FastChat

Further Reading

• https://chat.lmsys.org/
• https://lmsys.org/projects/

Overview

Guanaco is an LLM based off the QLoRA 4-bit finetuning method developed by Tim Dettmers et. al. in the UW NLP group. Guanaco achieves 99% ChatGPT performance on the Vicuna benchmark.

Guanaco is an LLM that uses a finetuning method called LoRA that was developed by Tim Dettmers et. al. in the UW NLP group. With QLoRA, it becomes possible to finetune up to a 65B parameter model on a 48GB GPU without loss of performance relative to a 16-bit model. The Guanaco model family outperforms all previously released models on the Vicuna benchmark. However, given the models are based off of the LLaMA model family, commercial use is not permitted.

Initial release: 2023-05-23

Reference

https://github.com/artidoro/qlora

Further Reading

• https://arxiv.org/abs/2305.14314
• https://twitter.com/Tim_Dettmers/status/1661379354507476994