Changes / Feeds / jinaai/jina-embeddings-v2-small-en
jinaai/jina-embeddings-v2-small-en
5 changes to a tracked key since 2023-09-27, newest first. Head as last read: 44e7d1d6caec8c883c2d4b207588504d519788d0.
GPU memory to fine-tune it, card by card: jina-embeddings-v2-small-en on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2023-10-26 | x_NXMC-2023-0018 | tokenizer model_max_length 8192 to 2147483648; truncation defaults change (2023-10-26).b63f8d36e312 -> 1c993a952ef4 |
| 2023-10-19 | x_NXMC-2023-0017 breaking | vocab_size changed from 30522 to 30528; the embedding and output head change shape, so adapters and merges made against the old vocabulary no longer load cleanly; derived parameters 32.4M to 32.4M (+3.1K, +0.00 GB of bf16 weights) (2023-10-19).cb8edc5e5c80 -> 8eac7ec07775 |
| 2023-10-19 | x_NXMC-2023-0016 breaking | vocab_size changed from 30528 to 30522; the embedding and output head change shape, so adapters and merges made against the old vocabulary no longer load cleanly; derived parameters 32.4M to 32.4M (-3.1K, -0.00 GB of bf16 weights) (2023-10-19).2a070b375b8c -> cb8edc5e5c80 |
| 2023-10-04 | x_NXMC-2023-0015 breaking | architectures ["JBertForMaskedLM"] to ["JinaBertForMaskedLM"]; a different class is instantiated from the same id (2023-10-04).e19c7cb8d583 -> f2416e24695d |
| 2023-10-02 | x_NXMC-2023-0014 breaking | derived parameters 28.5M to 32.4M (+3.9M, +0.01 GB of bf16 weights); context window 512 to 8192 tokens (2023-10-02).e462ab66a9e4 -> e19c7cb8d583 |
Pin it, and let a bot move the pin
from_pretrained("jinaai/jina-embeddings-v2-small-en", revision="44e7d1d6caec8c883c2d4b207588504d519788d0")
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/jinaai/jina-embeddings-v2-small-en.html)