A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
 Alpaca
|
 Dolly
|
|---|---|---|
| Developer | Stanford | Databricks |
| Current generation | – | – |
| Initial release | 2023-03-13 | 2023-03-24 |
| Instruct tuned | Yes | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | Noncommercial | MIT |
| Model sizes | 7B | 3B, 12B |
| Links |
Alpaca is an instruction-finetuned LLM based off of LLaMA.
The first of many instruct-finetuned versions of LLaMA, Alpaca is an instruction-following model introduced by Stanford researchers. Impressively, with only $600 of compute spend, the researchers demonstrated that on qualitative benchmarks Alpaca performed similarly to OpenAI's text-davinci-003, a significantly larger model.
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.
