Changes / Feeds / answerdotai/ModernBERT-base
answerdotai/ModernBERT-base
3 changes to a tracked key since 2024-12-11, newest first. Head as last read: 8949b909ec900327062f0ebf497f51aef5e6f0c8.
GPU memory to fine-tune it, card by card: ModernBERT-base on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-01-15 | x_NXMC-2025-0052 | tokenizer model_max_length 1e+30 to 8192; truncation defaults change (2025-01-15).94032bb66234 -> 8949b909ec90 |
| 2024-12-19 | x_NXMC-2024-0047 breaking | derived parameters 130.1M to 136.0M (+5.9M, +0.01 GB of bf16 weights); context window 512 to 8192 tokens (2024-12-19).fa3113d09d6d -> 5756c58a31a2 |
| 2024-12-11 | x_NXMC-2024-0046 breaking | architectures ["ModernBertModel"] to ["ModernBertForMaskedLM"]; a different class is instantiated from the same id (2024-12-11).cb3183fe4f51 -> 290243f4fe9b |
Pin it, and let a bot move the pin
from_pretrained("answerdotai/ModernBERT-base", revision="8949b909ec900327062f0ebf497f51aef5e6f0c8")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/answerdotai/ModernBERT-base.html)