OPT
Open Pre-trained Transformer Language Models (OPT) is part of the family of open source models designed to replicate GPT-3, with similar decoder-only architecture. It has since been superseded by models such as LLaMA, GPT-J, and Pythia.
A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
 OPT
|
 Vicuna
|
|---|---|---|
| Developer | Meta | UC Berkeley, CMU, Stanford, MBZUAI, UCSD |
| Current generation | – | – |
| Initial release | 2022-05-03 | 2023-03-30 |
| Instruct tuned | No | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | NA | Noncommercial |
| Model sizes | 1.3B, 2.7B, 6.7B, 13B, 30B, 66B, 175B | 13B |
| Links |
Open Pre-trained Transformer Language Models (OPT) is part of the family of open source models designed to replicate GPT-3, with similar decoder-only architecture. It has since been superseded by models such as LLaMA, GPT-J, and Pythia.
Released alongside Koala, Vicuna is one of many descendants of the Meta LLaMA model trained on dialogue data collected from the ShareGPT website. According to the authors, Vicuna achieves more than 90% of ChatGPT's quality in user preference tests, while vastly outperforming Alpaca. As of May 2023, Vicuna seems to be the heir apparent of the instruct-finetuned LLaMA model family, though it is also restricted from commercial use.