Flan-T5 XL
Google · 2022-10-20 · 2.8B parameters
Flan-T5 XL is the instruction-finetuned T5 v1.1 XL checkpoint from Google's 2022 FLAN scaling work, a 24-layer-per-stack encoder-decoder released as open weights. It applies the same broad instruction tuning, including chain-of-thought data, as the other Flan-T5 checkpoints; the paper rounds its size to 3B parameters, while the released checkpoint holds 2,849,757,184.
Benchmark scores
| Benchmark | Score |
|---|---|
| BBH (BIG-Bench Hard) | 35.2 |
| MGSM | 1.9 |
| MMLU | 52.4 |