StableVicuna
StableVicuna is an RLHF finetune of Vicuna using datasets such as the OpenAssistant Conversations Dataset and the GPT4All Prompt Generations dataset.
A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
 StableVicuna
|
 Vicuna
|
|---|---|---|
| Developer | Stability AI | UC Berkeley, CMU, Stanford, MBZUAI, UCSD |
| Current generation | – | – |
| Initial release | 2023-04-28 | 2023-03-30 |
| Instruct tuned | Yes | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | Noncommercial | Noncommercial |
| Model sizes | 13B | 13B |
| Links |
StableVicuna is an RLHF finetune of Vicuna using datasets such as the OpenAssistant Conversations Dataset and the GPT4All Prompt Generations dataset.
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.