Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

train-sentence-transformers

skill · huggingface/skillsApache-2.0 licenceAudited 13 Nov 2026 · source 33087d8174de

★ 11,341pushed 1 day ago
✓SAFEGrade B · 89/100 · 13 Nov 2026 · 33087d8
11,341repo stars · whole huggingface/skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 33087d8174de and found no filesystem, network or shell access and no hard-coded secrets. What it does: Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal),…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “train-sentence-transformers (huggingface/skills)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/huggingface/train-sentence-transformers

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

LOWSupply chainprompt.pipe_to_shell · references/hf_jobs_execution.md:9
F-08 Supply chainCWE-829 · CWE-1357Layer L2
- Access to the `hf_jobs()` MCP tool, or the `hf` CLI (`curl -LsSf https://hf.co/cli/install.sh | bash -s`).
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 33087d8174de · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherhuggingface GitHub organizationOwner of the repository this skill is read from
  • Source folderhuggingface/skills/skills/train-sentence-transformersThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict33087d8174deA new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal),…

---
name: train-sentence-transformers
description: Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
---

# Train a sentence-transformers Model

**This SKILL.md is a router, not a manual.** It tells you which references and example scripts to load for your task. The actual content (recommended losses, evaluators, training-script structure, model selection, training-arg knobs, troubleshooting) lives in `references/` and `scripts/`.

**Do not synthesize a training script from this file alone.** Open the per-type production template (`scripts/train_<type>_example.py`) and copy it as your starting point. The templates contain load-bearing scaffolding (autocast helper, model-card class, logger silencing list, `force=True`, `seed`, TF32, version-compatible imports, named-evaluator metric handling) that prior agent runs have repeatedly missed when rolling their own from a synthesized snippet.

## 1. Identify the model type

| Tag | Class | What it does | When to pick |
|---|---|---|---|
| **[SentenceTransformer]** | `SentenceTransformer` (bi-encoder) | Maps each input to a fixed-dim dense vector | Retrieval, similarity, clustering, classification, paraphrase mining, dedup |
| **[CrossEncoder]** | `CrossEncoder` (reranker) | Scores `(query, passage)` pairs jointly | Two-stage retrieval (rerank top-100 from bi-encoder), pair classification |
| **[SparseEncoder]** | `SparseEncoder` (SPLADE) | Sparse vectors over the vocabulary | Learned-sparse retrieval, inverted-index backends (Elasticsearch / OpenSearch / Lucene) |
| **[MultiVectorEncoder]** | `MultiVectorEncoder` (ColBERT) | One embedding per token, scored with MaxSim | Late-interaction retrieval, recall gains over bi-encoders at higher storage cost, multimodal (ColPali / ColQwen2) |

Tiebreakers when the request is ambiguous: "embedding model" / "vector search" / "similarity" → **[SentenceTransformer]**. "rerank" / "ranker" / "two-stage" → **[CrossEncoder]**. "SPLADE" / "sparse" / "inverted index" → **[SparseEncoder]**. "ColBERT" / "late interaction" / "multi-vector" / "MaxSim" / "ColPali" / "ColQwen" → **[MultiVectorEncoder]**. If still unclear, ask.

## 2. Required reading

**Read these in full before writing any code. Do not triage by perceived relevance.**

### Per-type: always required

**[SentenceTransformer]**
- `references/losses_sentence_transformer.md`: loss-to-data-shape mapping, `BatchSamplers.NO_DUPLICATES` requirement for MNRL-family, `Cached*` ↔ `gradient_checkpointing` incompatibility.
- `references/evaluators_sentence_transformer.md`: evaluator-to-task mapping, `metric_for_best_model` key construction (named vs unnamed), per-evaluator `primary_metric` values.
- `references/model_architectures.md`: encoder vs decoder vs static vs Router pipelines, pooling rules (mean / cls / lasttoken), auto-mean-pooling behavior for fresh-start MLM bases.
- `scripts/train_sentence_transformer_example.py`: production template. Copy this as your starting point.

**[CrossEncoder]**
- `references/losses_cross_encoder.md`: pointwise / pairwise / listwise / distillation, `pos_weight` derivation, `activation_fn=Identity()` mandatory for non-BCE losses (silent eval-rank collapse otherwise).
- `references/evaluators_cross_encoder.md`: `CrossEncoderRerankingEvaluator` recipe, named-evaluator key format `eval_{name}_{primary_metric}`.
- `scripts/train_cross_encoder_example.py`: production template. Copy this as your starting point.

**[SparseEncoder]**
- `references/losses_sparse_encoder.md`: `SpladeLoss` wrapper requirement, FLOPS regularizer weights, smoke-test active-dim ramp behavior.
- `references/evaluators_sparse_encoder.md`: `SparseNanoBEIREvaluator` (English-only) and the in-domain alternative, `eval_{name}_{primary_metric}` key format.
- `scripts/train_sparse_encoder_example.py`: production template. Copy this as your starting point.

**[MultiVectorEncoder]**
- `references/losses_multi_vector_encoder.md`: MaxSim scoring, scale choice per scoring mode (`scale=1.0` for MaxSim, roughly the average query length for MeanMaxSim), MNRL / CachedMNRL / MarginMSE / DistillKLDiv, XTR-vs-ColBERT scoring, CachedMNRL ↔ `gradient_checkpointing` incompatibility.
- `references/evaluators_multi_vector_encoder.md`: `MultiVectorNanoBEIREvaluator` (English-only) and the in-domain alternative, `eval_NanoBEIR_mean_maxsim_ndcg@10` key format, distillation-eval spearman variant.
- `scripts/train_multi_vector_encoder_example.py`: production template. Copy this as your starting point.

### Cross-cutting: always required (regardless of task)

- `references/training_args.md`: `TrainingArguments` knobs, precision rules (load fp32 + autocast bf16/fp16, never `torch_dtype=bfloat16`), `warmup_steps` (float) vs deprecated `warmup_ratio`, `save_steps` must be a multiple of `eval_steps` for `load_best_model_at_end`, schedulers, HPO, tracker, resume, hub-push variants.
- `references/dataset_formats.md`: column-matching rules (label name auto-detection, column-order-not-name), reshaping recipes, hard-negative mining options.
- `references/base_model_selection.md`: discovery commands, per-type model namespaces, ModernBERT-family `max_seq_length=8192` trap, `datasets >= 4` script-loader rejection, non-English starting-point shortcuts.
- `references/troubleshooting.md`: symptom-indexed failure recipes. Skim the section headings on every run, even a healthy one. The "Metrics don't improve" and "Hub

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 33087d8

Download folder ↗
pip install "sentence-transformers[train]>=5.0"        # add [train,image] / [audio] / [video] for [SentenceTransformer] multimodal
pip install trackio                                    # optional tracker (or wandb / tensorboard / mlflow)

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 33087d8174de only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 33087d8174de

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/huggingface/train-sentence-transformers/badge.svg)](https://modelsatlas.com/skills/huggingface/train-sentence-transformers/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/huggingface/train-sentence-transformers/badge.svg)](https://modelsatlas.com/skills/huggingface/train-sentence-transformers/)

Questions about train-sentence-transformers

What does the train-sentence-transformers skill do?
Give your agents the power of the Hugging Face ecosystem
Is train-sentence-transformers safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can train-sentence-transformers access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does train-sentence-transformers work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (33087d8174de), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.