ClaudeSuperPower
SubmitLog in

train-sentence-transformers

Skill

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 classificatio

0Machine Learning

Install

git clone https://github.com/huggingface/skills.git ~/.claude/skills/train-sentence-transformers

What is train-sentence-transformers?

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), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~140 tokens of context used while enabled, before you invoke anything

Documentation

README · ~4 min read

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

TagClassWhat it doesWhen to pick
[SentenceTransformer]SentenceTransformer (bi-encoder)Maps each input to a fixed-dim dense vectorRetrieval, similarity, clustering, classification, paraphrase mining, dedup
[CrossEncoder]CrossEncoder (reranker)Scores (query, passage) pairs jointlyTwo-stage retrieval (rerank top-100 from bi-encoder), pair classification
[SparseEncoder]SparseEncoder (SPLADE)Sparse vectors over the vocabularyLearned-sparse retrieval, inverted-index backends (Elasticsearch / OpenSearch / Lucene)

Tiebreakers when the request is ambiguous: "embedding model" / "vector search" / "similarity" → [SentenceTransformer]. "rerank" / "ranker" / "two-stage" → [CrossEncoder]. "SPLADE" / "sparse" / "inverted index" → [SparseEncoder]. If still unclear, ask.

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.