Changes / Feeds / cross-encoder/ms-marco-MiniLM-L2-v2
cross-encoder/ms-marco-MiniLM-L2-v2
2 changes to a tracked key since 2021-04-15, newest first. Head as last read: 1b5cd67b15209f24824c50370e0397743aa9b787.
Declares cross-encoder/ms-marco-MiniLM-L12-v2 as its base but has a different set of tensors: 42 align (40 of them changed), 0 are new and 160 of the base's are gone. Compared tensor by tensor from sha256 fingerprints: 1b5cd67b1520 against cross-encoder/ms-marco-MiniLM-L12-v2 at 7b0235231ca2. A hash is equal or not; it says nothing about what an edit does.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-04-08 | x_NXMC-2025-0192 breaking | tokenizer_class unset to "BertTokenizer" (2025-04-08).fa5f4d9c69e0 -> c64fde414860 Open in app |
| 2021-04-15 | x_NXMC-2021-0010 | tokenizer model_max_length unset to 512; truncation defaults change (2021-04-15).0957858e61da -> fa5f4d9c69e0 Open in app |
Pin it, and let a bot move the pin
from_pretrained("cross-encoder/ms-marco-MiniLM-L2-v2", revision="1b5cd67b15209f24824c50370e0397743aa9b787")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/cross-encoder/ms-marco-MiniLM-L2-v2.html)