chore(deps): bump sentence-transformers from 5.6.1 to 5.7.0 in /backend/python/transformers

[dependabot]

Bumps sentence-transformers from 5.6.1 to 5.7.0.

Release notes

Sourced from sentence-transformers's releases.

v5.7.0 - GradCache Overhaul, torch.compile Inference, and a Large Batch of Correctness Fixes

This minor version is a correctness and performance-focused release. It rebuilds all gradient-cached losses on one shared engine, fixing several silently wrong gradients and adding token-based mini-batching for up to 3.9x faster cached-loss training. It also makes model.compile() actually speed up inference, and brings a long list of fixes across embedding quantization, evaluators, hard-negative mining, community detection, and multimodal inputs.

Two changes are marked breaking (🚨): int8/uint8 embedding quantization now clips out-of-range values and floors bucket values, so int8 outputs are no longer bit-identical with earlier versions, and AdaptiveLayerLoss/Matryoshka2dLoss now weight prior-layer losses uniformly by default. There's also a forward-looking deprecation: loading models whose modules import classes from outside sentence_transformers will require trust_remote_code=True from v6.0.

Install this version with

# Training + Inference
pip install sentence-transformers[train]==5.7.0
Inference only, use one of:
pip install sentence-transformers==5.7.0
pip install sentence-transformers[onnx-gpu]==5.7.0
pip install sentence-transformers[onnx]==5.7.0
pip install sentence-transformers[openvino]==5.7.0
Multimodal dependencies (optional):
pip install sentence-transformers[image]==5.7.0
pip install sentence-transformers[audio]==5.7.0
pip install sentence-transformers[video]==5.7.0
Or combine as needed:
pip install sentence-transformers[train,onnx,image]==5.7.0

GradCache overhaul: correct gradients and token-based mini-batching (#3862)

The gradient-cached losses (CachedMultipleNegativesRankingLoss, CachedGISTEmbedLoss, CachedSpladeLoss, the Cross Encoder CachedMultipleNegativesRankingLoss, and MegaBatchMarginLoss) train with large batch sizes at constant memory by embedding in mini-batches and replaying them with cached gradients. Each loss carried its own diverged copy of that machinery. They are now all rebuilt on one shared engine, which fixed several bugs that silently corrupted gradients:

• Cross Encoder CachedMultipleNegativesRankingLoss on GPU: the backward pass used different dropout masks than the forward pass, silently biasing gradients for every reranker trained with dropout active on CUDA or MPS. CPU training was unaffected.
• Running two forward passes before a backward pass (e.g. in custom training loops) made CachedGISTEmbedLoss and the Cross Encoder loss backpropagate the wrong batch's gradients, because the cache was stored on the loss module. The cache now travels with each forward pass's backward hook (the .cache and .random_states loss attributes are gone as a result).
• Pooling(include_prompt=False) (e.g. Instructor models) mutated the attention mask in place, so the backward re-embedding of every cached loss ran with a different mask than the forward pass.
• MatryoshkaLoss(GISTEmbedLoss(...)): the guide model overwrote the cached embeddings, so only the largest Matryoshka dimension was actually trained.

Along the way, this also fixed an autocast dtype crash in the backward pass and the trainer retaining autograd graphs between logging steps when tracking loss components.

MegaBatchMarginLoss's default mini-batched version is rebuilt on the engine as well. It crashed outright on recent releases, and underneath that, its historical implementation only applied the last mini-batch's gradients. It now trains on the full batch (results will differ, for the better), works with MatryoshkaLoss, evaluates under torch.no_grad, and raises for a third input column instead of silently ignoring it.

The headline feature is mini_batch_num_tokens, available on CachedMultipleNegativesRankingLoss, CachedMultipleNegativesSymmetricRankingLoss, CachedGISTEmbedLoss, CachedSpladeLoss, and MegaBatchMarginLoss. Instead of a fixed number of sequences per mini-batch, mini-batches are greedily packed by total non-padding token count, giving near-constant work per mini-batch on variable-length data:

from sentence_transformers import SentenceTransformer
from sentence_transformers.sentence_transformer.losses import CachedMultipleNegativesRankingLoss
model = SentenceTransformer("microsoft/mpnet-base")
loss = CachedMultipleNegativesRankingLoss(model, mini_batch_num_tokens=16384)

On the PR's Natural Questions benchmark, cached-loss training with flash attention and a tuned token budget dropped from 715 to 182 seconds (3.9x) versus the previous release, with unchanged quality. The engine also trims trailing padding from each mini-batch, which alone is worth about 26% throughput on the default padded path. The updated training efficiency documentation recommends the smallest token budget that saturates your GPU. mini_batch_size keeps working everywhere as before.

... (truncated)

Commits

• b2a9529 [fix] Name the lone suggested parameter in the mine_hard_negatives missing-ne...
• 00e696c Release v5.7.0
• b69081a [fix] Treat a 1-dimensional query embedding as a single query in semantic_sea...
• c9c4250 Keep queries aligned in semantic_search_seismic when a query matches nothing ...
• 6d331a5 [fix] Support mixed sparse/dense inputs in euclidean and manhattan similari...
• 68c8cda [fix] Reject num_negatives larger than the range_min/range_max window in mine...
• cfb6d43 [trainer] Fix eval DataLoader worker leak with dataloader_persistent_worker...
• f6d3a40 Expand the community window on ties with the threshold (#3900)
• 0b3fcbd Correct the corpus_precision values documented for semantic_search_faiss ...
• 62724e7 Drop FAISS padding placeholders from semantic_search_faiss results (#3887)
• Additional commits viewable in compare view