Dolly
Dolly is an LLM trained using the Databricks machine learning platform. Originally released without instruct-finetuning, Dolly v2 included tuning on the Stanford Alpaca dataset.
A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
 Dolly
|
 StableVicuna
|
|---|---|---|
| Developer | Databricks | Stability AI |
| Current generation | – | – |
| Initial release | 2023-03-24 | 2023-04-28 |
| Instruct tuned | Yes | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | MIT | Noncommercial |
| Model sizes | 3B, 12B | 13B |
| Links |
Dolly is an LLM trained using the Databricks machine learning platform. Originally released without instruct-finetuning, Dolly v2 included tuning on the Stanford Alpaca dataset.
StableVicuna is an RLHF finetune of Vicuna using datasets such as the OpenAssistant Conversations Dataset and the GPT4All Prompt Generations dataset.