Changes / Feeds / cross-encoder/ms-marco-MiniLM-L4-v2
cross-encoder/ms-marco-MiniLM-L4-v2
2 changes to a tracked key since 2021-04-15, newest first. Head as last read: 777b2f369bc1c2f850df8bd367ed1654bda4497b.
Declares cross-encoder/ms-marco-MiniLM-L12-v2 as its base but has a different set of tensors: 74 align (72 of them changed), 0 are new and 128 of the base's are gone. Compared tensor by tensor from sha256 fingerprints: 777b2f369bc1 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-2025-0185 breaking | tokenizer_class unset to "BertTokenizer" (2025-04-08).bb12094642d0 -> 739b035daeca Open in app |
| 2021-04-15 | x_NXMC-2021-0005 | tokenizer model_max_length unset to 512; truncation defaults change (2021-04-15).8f5be2b74537 -> bb12094642d0 Open in app |
Pin it, and let a bot move the pin
from_pretrained("cross-encoder/ms-marco-MiniLM-L4-v2", revision="777b2f369bc1c2f850df8bd367ed1654bda4497b")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-L4-v2.html)