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 | LAION | |
| Current generation | – | – |
| Initial release | 2023-03-03 | 2023-04-15 |
| Instruct tuned | Yes | Yes |
| Coding | No | No |
| Finetuning | Yes | Yes |
| Open source | Yes | Yes |
| License | Apache 2.0 | Varies |
| Model sizes | 20B | 6.7B, 6.9B, 7B, 12B, 30B |
| 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.
OpenAssistant is a project organized by LAION with aim of providing an open source alternative to ChatGPT. Its primary effort is to collected instruct examples to then tune existing LLMs. The first major release is available as part of Hugging Face's HuggingChat.