A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
 FastChat
|
 Koala
|
|---|---|---|
| Developer | LMSYS | BAIR |
| Current generation | – | – |
| Initial release | 2023-04-28 | 2023-04-03 |
| Instruct tuned | Yes | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | Apache 2.0 | Noncommercial |
| Model sizes | 3B | 7B, 13B |
| Links |
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.
Released alongside Vicuna, Koala is one of many descendants of the Meta LLaMA model trained on dialogue data collected from the web. On the developers' benchmarks, Koala outperforms its sibling Alpaca, though its adoption has been significantly less than that of its other sibling, Vicuna. Due to its use of LLaMA, only research use is permitted.
