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 It has since been superseded by models such as LLaMA, GPT-J, and Pythia.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
|
 Pythia
|
|---|---|---|
| Developer | Meta | EleutherAI, Together |
| Current generation | – | – |
| Initial release | 2022-05-03 | 2023-02-13 |
| Instruct tuned | No | No |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | NA | Apache 2.0 |
| Model sizes | 1.3B, 2.7B, 6.7B, 13B, 30B, 66B, 175B | 1B, 1.4B, 2.8B, 6.9B, 12B |
| 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 It has since been superseded by models such as LLaMA, GPT-J, and Pythia.
The most recent (as of May 2023) effort from EleutherAI, Pythia is a set of LLMs trained on The Pile. While it appears to outperform OPT and GPTNeo, its performance against GPT-J is unclear. Versions of Pythia have also been instruct-tuned by the team at Together.