Changes / Feeds / google-t5/t5-small
google-t5/t5-small
4 changes to a tracked key since 2019-12-11, newest first. Head as last read: df1b051c49625cf57a3d0d8d3863ed4d13564fe4.
GPU memory to fine-tune it, card by card: t5-small on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2022-12-12 | x_NXMC-2022-0004 breaking | config.json was removed; whatever defaults it set now come from the library (2022-12-12).3ac06c3177fe -> c2bea447bc4e |
| 2020-04-24 | x_NXMC-2020-0032 breaking | EOS declared as 1 (was unset); generation that relied on the library default now stops on this token; model_type declared as "t5" (was unset); pad token unset to 0; batched training masks a different id (2020-04-24).00f126a8df80 -> 3ac06c3177fe |
| 2020-03-26 | x_NXMC-2020-0031 breaking | config.json was removed; whatever defaults it set now come from the library (2020-03-26).e87f2a02b2fa -> 8c5d40ac989b |
| 2020-01-31 | x_NXMC-2020-0030 | architectures declared as ["T5WithLMHeadModel"] (was unset) (2020-01-31).c9c2c8f7fe6a -> e87f2a02b2fa |
Pin it, and let a bot move the pin
from_pretrained("google-t5/t5-small", revision="df1b051c49625cf57a3d0d8d3863ed4d13564fe4")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/google-t5/t5-small.html)