FLAN-UL2
Similar to FLAN-T5, FLAN-UL2 is a model based on Google's popular T5 architecture with an upgraded pre-training procedure dubbed UL2. On most NLU benchmarks, FLAN-UL2 outperforms FLAN-T5 by a significant margin.
A side-by-side comparison of release history, capabilities, licensing and model sizes.
| Attribute |
|
|
|---|---|---|
| Developer | Nomic AI | |
| Current generation | – | – |
| Initial release | 2023-03-03 | 2023-03-26 |
| Instruct tuned | Yes | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | Apache 2.0 | Varies |
| Model sizes | 20B | 7B, 13B |
| Links |
Similar to FLAN-T5, FLAN-UL2 is a model based on Google's popular T5 architecture with an upgraded pre-training procedure dubbed UL2. On most NLU benchmarks, FLAN-UL2 outperforms FLAN-T5 by a significant margin.
Describing itself as an ecosystem for open-source chatbots, Nomic provides a framework for training LLMs with LLaMA and GPT-J backbones.