Update sentence-transformers requirement from ~=5.4.1 to ~=5.5.0 (#314)

Updates the requirements on
[sentence-transformers](https://github.com/huggingface/sentence-transformers)
to permit the latest version.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/huggingface/sentence-transformers/releases">sentence-transformers's
releases</a>.</em></p>
<blockquote>
<h2>v5.5.0 - Training Agent Skill, EmbedDistillLoss, and ADRMSELoss</h2>
<p>This release ships the <code>train-sentence-transformers</code> Agent
Skill, adds two new training losses, and brings a long list of
robustness and correctness fixes.</p>
<p>The new <code>train-sentence-transformers</code> Agent Skill lets AI
coding agents (Claude Code, Codex, Cursor, Gemini CLI, ...) drive
end-to-end training and fine-tuning across all three model types.
<code>EmbedDistillLoss</code> is a new embedding-level knowledge
distillation loss for <code>SentenceTransformer</code>: it aligns a
student model's embeddings with pre-computed teacher embeddings, an
alternative to the score-based distillation provided by
<code>MarginMSELoss</code> and <code>DistillKLDivLoss</code>.
<code>ADRMSELoss</code> is a new listwise learning-to-rank loss for
<code>CrossEncoder</code> from the Rank-DistiLLM paper.
<code>encode()</code> and <code>predict()</code> also gain a per-call
<code>processing_kwargs</code> override, and more.</p>
<p>Install this version with</p>
<pre lang="bash"><code># Training + Inference
pip install sentence-transformers[train]==5.5.0
<h1>Inference only, use one of:</h1>
<p>pip install sentence-transformers==5.5.0
pip install sentence-transformers[onnx-gpu]==5.5.0
pip install sentence-transformers[onnx]==5.5.0
pip install sentence-transformers[openvino]==5.5.0</p>
<h1>Multimodal dependencies (optional):</h1>
<p>pip install sentence-transformers[image]==5.5.0
pip install sentence-transformers[audio]==5.5.0
pip install sentence-transformers[video]==5.5.0</p>
<h1>Or combine as needed:</h1>
<p>pip install sentence-transformers[train,onnx,image]==5.5.0
</code></pre></p>
<h2>The <code>train-sentence-transformers</code> Agent Skill (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3752">#3752</a>)</h2>
<p>If you use an AI coding agent (Claude Code, Codex, Cursor, Gemini
CLI, OpenCode, ...), you can now install the <a
href="https://github.com/huggingface/sentence-transformers/tree/main/skills"><code>train-sentence-transformers</code></a>
Agent Skill and ask your agent to fine-tune a model on your data:</p>
<pre lang="bash"><code>hf skills add train-sentence-transformers #
installs under ./.agents/skills/
hf skills add train-sentence-transformers --global # installs under
~/.agents/skills/
hf skills add train-sentence-transformers --claude # also symlinks into
.claude/skills/
</code></pre>
<p>The skill gives the agent curated, version-aware guidance for
training <code>SentenceTransformer</code> (bi-encoder),
<code>CrossEncoder</code> (reranker), and
<code>SparseEncoder</code>/SPLADE models, covering base model selection,
loss and evaluator choice, hard-negative mining, distillation, LoRA,
Matryoshka, multilingual training, static embeddings, plus a set of
production-ready training template scripts. Then you can prompt your
agent with things like:</p>
<blockquote>
<p>&quot;Train a multilingual sentence-transformer on Dutch legal
pairs.&quot;</p>
<p>&quot;Fine-tune a cross-encoder reranker on <code>(question,
answer)</code> pairs from my dataset, mine hard negatives, and push to
my Hub repo.&quot;</p>
<p>&quot;Train a German sparse embedding model with high
sparsity.&quot;</p>
<p>&quot;Can you train a static embedding model on 100k code
triplets?&quot;</p>
</blockquote>
<p>The skill lives in the repository under <a
href="https://github.com/huggingface/sentence-transformers/tree/main/skills"><code>skills/train-sentence-transformers/</code></a>
and is mirrored to the <a
href="https://github.com/huggingface/skills"><code>huggingface/skills</code></a>
marketplace on each release.</p>
<h2>New loss: EmbedDistillLoss (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3665">#3665</a>)</h2>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/f9f3269c7bd548555b7273a5378d52eeaa5d6286"><code>f9f3269</code></a>
Merge branch 'main' into v5.5-release</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/02dc21d77dfd22b5816fb5398877253100b89b43"><code>02dc21d</code></a>
Update index tip for v5.5.0 (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3774">#3774</a>)</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/833828b3dae0cf9e6943ae01b9c9645f883daf3b"><code>833828b</code></a>
Release v5.5.0</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/98ac358861359fd275824732e5f658b2f4ca6c78"><code>98ac358</code></a>
[<code>docs</code>] Load models in float32 in the training examples
&amp; docs (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3773">#3773</a>)</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/d8ee0410ba140f41aa2ac0735a97e1d690dd2df5"><code>d8ee041</code></a>
[<code>docs</code>] Use modality-neutral terms (input, document) in loss
docs &amp; docstrin...</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/4c6850e444e5bcedfb026e9d674ae18c19ab5233"><code>4c6850e</code></a>
[<code>examples</code>] Avoid LoggingHandler, silence httpx in examples
(<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3771">#3771</a>)</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/1418823d250763751ea95212dfb9ecaa919f5e92"><code>1418823</code></a>
docs: fix grammar in parallel-sentence-mining README (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3769">#3769</a>)</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/22a383d3644cfaa40038adb0b70a9320f7f73d36"><code>22a383d</code></a>
[<code>docs</code>] Use direct class imports in examples &amp; docs
(drop `losses.MSELoss(.....</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/68e4d61c97d16393e4e4994232cda4dd02a1d1b9"><code>68e4d61</code></a>
[<code>fix</code>] Unwrap DDP/torch.compile wrappers in
<code>AdaptiveLayerLoss</code> (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3768">#3768</a>)</li>
<li><a
href="https://github.com/huggingface/sentence-transformers/commit/815175000855be81d0df10dae610cf8b4f06ef7a"><code>8151750</code></a>
[<code>fix</code>] Use first non-pad token for CLS pooling with
left-padding (<a
href="https://redirect.github.com/huggingface/sentence-transformers/issues/3767">#3767</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/huggingface/sentence-transformers/compare/v5.4.1...v5.5.0">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Author: DefinetlyNotAI

requirements.txt

@@ -17,4 +17,4 @@ networkx~=3.6.1
 pandas~=3.0.3
 cryptography~=48.0.0
 scapy~=2.7.0
-sentence-transformers~=5.4.1
+sentence-transformers~=5.5.0